{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"junk property Classification Industry level.ipynb","provenance":[{"file_id":"1WLR8rPLjxiTQNyuV4uXBfVx1Ni4LSXBp","timestamp":1605693223282},{"file_id":"1lPNcI9eIO_givFo1Rwd0-05JP1PY9odj","timestamp":1603705018259}],"collapsed_sections":[],"authorship_tag":"ABX9TyNXcmcr6z/af6vlpc1SM+F7"},"kernelspec":{"name":"python3","display_name":"Python 3"}},"cells":[{"cell_type":"code","metadata":{"id":"0buwUZkZwbqa","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605793177512,"user_tz":-330,"elapsed":1251,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"77d1f38c-709e-446b-fc44-41e1bba722c3"},"source":["from google.colab import drive\n","drive.mount('/content/drive')"],"execution_count":43,"outputs":[{"output_type":"stream","text":["Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"--TudwOjzdHJ","colab":{"base_uri":"https://localhost:8080/","height":226},"executionInfo":{"status":"ok","timestamp":1605793178105,"user_tz":-330,"elapsed":1602,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"7aa99f1e-ff92-4fc0-815d-a08889f29eea"},"source":["import pandas as pd\n","import numpy as np\n","import warnings \n","warnings.filterwarnings(\"ignore\")\n","import pandas_profiling as pp\n","from sklearn.preprocessing import LabelBinarizer\n","from sklearn.ensemble import RandomForestClassifier\n","from sklearn.model_selection import train_test_split, GridSearchCV, StratifiedKFold\n","from sklearn.metrics import roc_curve, precision_recall_curve, auc, make_scorer, recall_score, accuracy_score, precision_score, confusion_matrix, fbeta_score, roc_auc_score\n","from sklearn.model_selection import train_test_split\n","from sklearn.metrics import classification_report as cr\n","\n","import matplotlib.pyplot as plt\n","plt.style.use(\"ggplot\")\n","df = pd.read_csv('/content/drive/My Drive/collab projects/Classification Project Industry Dataset/Property_train.csv', parse_dates=True)\n","df.head()"],"execution_count":44,"outputs":[{"output_type":"execute_result","data":{"text/html":["
\n","\n","\n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n","
JunkInteriorsStylePriceIndex8ListDateMaterialPriceIndex9AgencyAreaIncomeTypeEnvRatingPriceIndex7ExpeditedListingPriceIndex4PriceIndex1PriceIndex6PRIMEUNITChannelZipInsurancePremiumIndexPlotTypeArchitecturePriceIndex3RegionPriceIndex5SubModelFacadeStateNormalisedPopulationBuildYearRegionTypePropertyAgePriceIndex2
006LLJ14674.09/7/2010UT7W8270CAT3Bmissing13143.0014224.09217.010387.0missingDirect21075623WHBII3Z913108.0A9022.06E9GGREENMD420772008A210692.0
11XZ9F4172.01/7/2009PRN03890CAT2Bmissing3461.004404.02958.03400.0missingDirect731291689WHBIAVYP3695.0A2742.0FIVQSILVEROK772582002A73615.0
20QWEV8210.06/23/2010A9RA5900CAT1Bmissing6922.008952.04568.04862.0missingOther296972351W62B1M5X7730.0A3768.04K0HSILVERSC945142004A65805.0
30MK2K7309.03/19/2009RRJQ7460OTHERAmissing6300.007460.05361.06305.0missingAgent282731933WLQ6DKOO6290.0A5370.0ZLXYWHITENC823022002C76444.0
40GK4G9182.03/3/2010HE5A6400OTHERBmissing8330.009846.05428.05718.0missingOther29697482WHBIKML68583.0A4803.0FIVQSILVERSC491762007B36286.0
\n","
"],"text/plain":[" Junk InteriorsStyle PriceIndex8 ... RegionType PropertyAge PriceIndex2\n","0 0 6LLJ 14674.0 ... A 2 10692.0\n","1 1 XZ9F 4172.0 ... A 7 3615.0\n","2 0 QWEV 8210.0 ... A 6 5805.0\n","3 0 MK2K 7309.0 ... C 7 6444.0\n","4 0 GK4G 9182.0 ... B 3 6286.0\n","\n","[5 rows x 31 columns]"]},"metadata":{"tags":[]},"execution_count":44}]},{"cell_type":"code","metadata":{"id":"g0e6tw4uzdKc","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605793178107,"user_tz":-330,"elapsed":1376,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"475d451d-c1f6-4d5e-d1df-85ef90207a78"},"source":["print(df.shape)"],"execution_count":45,"outputs":[{"output_type":"stream","text":["(62035, 31)\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"Ao0qhZOd0blO","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605793178110,"user_tz":-330,"elapsed":723,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"bbb99cc4-2479-435b-d787-bdcc2962c92e"},"source":["df.columns"],"execution_count":46,"outputs":[{"output_type":"execute_result","data":{"text/plain":["Index(['Junk', 'InteriorsStyle', 'PriceIndex8', 'ListDate', 'Material',\n"," 'PriceIndex9', 'Agency', 'AreaIncomeType', 'EnvRating', 'PriceIndex7',\n"," 'ExpeditedListing', 'PriceIndex4', 'PriceIndex1', 'PriceIndex6',\n"," 'PRIMEUNIT', 'Channel', 'Zip', 'InsurancePremiumIndex', 'PlotType',\n"," 'Architecture', 'PriceIndex3', 'Region', 'PriceIndex5', 'SubModel',\n"," 'Facade', 'State', 'NormalisedPopulation', 'BuildYear', 'RegionType',\n"," 'PropertyAge', 'PriceIndex2'],\n"," dtype='object')"]},"metadata":{"tags":[]},"execution_count":46}]},{"cell_type":"code","metadata":{"id":"hkhrRWmL07sd","colab":{"base_uri":"https://localhost:8080/","height":300},"executionInfo":{"status":"ok","timestamp":1605793178844,"user_tz":-330,"elapsed":1172,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"0a57e2c7-2636-4ef0-be3d-3454c0b7daa2"},"source":["df.describe()"],"execution_count":47,"outputs":[{"output_type":"execute_result","data":{"text/html":["
\n","\n","\n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n","
JunkPriceIndex9ExpeditedListingZipInsurancePremiumIndexNormalisedPopulationBuildYearPropertyAge
count62035.00000062035.00000062035.00000062035.00000062035.00000062035.00000062035.00000062035.00000
mean0.1225446731.4447650.02468058038.1491091277.28685471462.6943022005.3477394.17171
std0.3279151766.1308060.15514826143.635828600.78770814583.0795781.7300141.70878
min0.000000225.0000000.0000002764.000000462.0000004825.0000002001.0000000.00000
25%0.0000005430.0000000.00000032124.000000837.00000061803.5000002004.0000003.00000
50%0.0000006705.0000000.00000073108.0000001155.00000073361.0000002005.0000004.00000
75%0.0000007900.0000000.00000080022.0000001623.00000082370.5000002007.0000005.00000
max1.00000038785.0000001.00000099224.0000007498.000000115717.0000002010.0000009.00000
\n","
"],"text/plain":[" Junk PriceIndex9 ... BuildYear PropertyAge\n","count 62035.000000 62035.000000 ... 62035.000000 62035.00000\n","mean 0.122544 6731.444765 ... 2005.347739 4.17171\n","std 0.327915 1766.130806 ... 1.730014 1.70878\n","min 0.000000 225.000000 ... 2001.000000 0.00000\n","25% 0.000000 5430.000000 ... 2004.000000 3.00000\n","50% 0.000000 6705.000000 ... 2005.000000 4.00000\n","75% 0.000000 7900.000000 ... 2007.000000 5.00000\n","max 1.000000 38785.000000 ... 2010.000000 9.00000\n","\n","[8 rows x 8 columns]"]},"metadata":{"tags":[]},"execution_count":47}]},{"cell_type":"code","metadata":{"id":"vRAu5srO1Zv7","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605793179291,"user_tz":-330,"elapsed":1344,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"4e14f16e-2176-4caa-9431-884474d41f5b"},"source":["list(zip(df.columns,df.dtypes,df.nunique()))"],"execution_count":48,"outputs":[{"output_type":"execute_result","data":{"text/plain":["[('Junk', dtype('int64'), 2),\n"," ('InteriorsStyle', dtype('O'), 1036),\n"," ('PriceIndex8', dtype('O'), 12686),\n"," ('ListDate', dtype('O'), 516),\n"," ('Material', dtype('O'), 134),\n"," ('PriceIndex9', dtype('int64'), 2019),\n"," ('Agency', dtype('O'), 5),\n"," ('AreaIncomeType', dtype('O'), 4),\n"," ('EnvRating', dtype('O'), 3),\n"," ('PriceIndex7', dtype('O'), 12078),\n"," ('ExpeditedListing', dtype('int64'), 2),\n"," ('PriceIndex4', dtype('O'), 13006),\n"," ('PriceIndex1', dtype('O'), 10053),\n"," ('PriceIndex6', dtype('O'), 10863),\n"," ('PRIMEUNIT', dtype('O'), 3),\n"," ('Channel', dtype('O'), 3),\n"," ('Zip', dtype('int64'), 152),\n"," ('InsurancePremiumIndex', dtype('int64'), 277),\n"," ('PlotType', dtype('O'), 13),\n"," ('Architecture', dtype('O'), 33),\n"," ('PriceIndex3', dtype('O'), 12309),\n"," ('Region', dtype('O'), 3),\n"," ('PriceIndex5', dtype('O'), 10011),\n"," ('SubModel', dtype('O'), 831),\n"," ('Facade', dtype('O'), 17),\n"," ('State', dtype('O'), 37),\n"," ('NormalisedPopulation', dtype('int64'), 36675),\n"," ('BuildYear', dtype('int64'), 10),\n"," ('RegionType', dtype('O'), 5),\n"," ('PropertyAge', dtype('int64'), 10),\n"," ('PriceIndex2', dtype('O'), 11010)]"]},"metadata":{"tags":[]},"execution_count":48}]},{"cell_type":"code","metadata":{"id":"JDTu0U8RAcbC","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605793184835,"user_tz":-330,"elapsed":856,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"13ebe2b3-90f2-429a-c238-9388fd450684"},"source":["cutoff = (5/100)* df.shape[0]\n","cutoff"],"execution_count":49,"outputs":[{"output_type":"execute_result","data":{"text/plain":["3101.75"]},"metadata":{"tags":[]},"execution_count":49}]},{"cell_type":"code","metadata":{"id":"UJlX9NLaAyMJ","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605793193909,"user_tz":-330,"elapsed":834,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"16de346f-211c-4ec9-a2f8-1b14815780b4"},"source":["numcol = [\"PriceIndex5\",\"PriceIndex7\",\"PriceIndex4\",\"PriceIndex1\",\"PriceIndex6\",\"PriceIndex2\",\"PriceIndex3\",\"PriceIndex8\", \"PriceIndex9\"]\n","for col in numcol:\n"," df[col] = pd.to_numeric(df[col], errors=\"coerce\")\n","list(zip(df.columns,df.dtypes,df.nunique()))"],"execution_count":50,"outputs":[{"output_type":"execute_result","data":{"text/plain":["[('Junk', dtype('int64'), 2),\n"," ('InteriorsStyle', dtype('O'), 1036),\n"," ('PriceIndex8', dtype('float64'), 12685),\n"," ('ListDate', dtype('O'), 516),\n"," ('Material', dtype('O'), 134),\n"," ('PriceIndex9', dtype('int64'), 2019),\n"," ('Agency', dtype('O'), 5),\n"," ('AreaIncomeType', dtype('O'), 4),\n"," ('EnvRating', dtype('O'), 3),\n"," ('PriceIndex7', dtype('float64'), 12077),\n"," ('ExpeditedListing', dtype('int64'), 2),\n"," ('PriceIndex4', dtype('float64'), 13005),\n"," ('PriceIndex1', dtype('float64'), 10052),\n"," ('PriceIndex6', dtype('float64'), 10862),\n"," ('PRIMEUNIT', dtype('O'), 3),\n"," ('Channel', dtype('O'), 3),\n"," ('Zip', dtype('int64'), 152),\n"," ('InsurancePremiumIndex', dtype('int64'), 277),\n"," ('PlotType', dtype('O'), 13),\n"," ('Architecture', dtype('O'), 33),\n"," ('PriceIndex3', dtype('float64'), 12308),\n"," ('Region', dtype('O'), 3),\n"," ('PriceIndex5', dtype('float64'), 10010),\n"," ('SubModel', dtype('O'), 831),\n"," ('Facade', dtype('O'), 17),\n"," ('State', dtype('O'), 37),\n"," ('NormalisedPopulation', dtype('int64'), 36675),\n"," ('BuildYear', dtype('int64'), 10),\n"," ('RegionType', dtype('O'), 5),\n"," ('PropertyAge', dtype('int64'), 10),\n"," ('PriceIndex2', dtype('float64'), 11009)]"]},"metadata":{"tags":[]},"execution_count":50}]},{"cell_type":"code","metadata":{"id":"i7Yzv4StCT2I","colab":{"base_uri":"https://localhost:8080/","height":506},"executionInfo":{"status":"ok","timestamp":1605781243120,"user_tz":-330,"elapsed":1445,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"ddd28fa3-aa79-42f9-b3b0-4792fcd3997b"},"source":["cols = df.select_dtypes([\"object\"])\n","for colname in cols:\n"," cats = df[colname].value_counts()\n"," keepcat = cats.index[cats >= cutoff]\n"," for cat in keepcat:\n"," if cat == \"missing\":\n"," continue\n"," name=colname+'_'+cat\n"," df[name] = (df[colname]==cat).astype(int)\n"," del df[colname]\n"," print(colname)\n","df.head()"],"execution_count":27,"outputs":[{"output_type":"stream","text":["InteriorsStyle\n","ListDate\n","Material\n","Agency\n","AreaIncomeType\n","EnvRating\n","PRIMEUNIT\n","Channel\n","PlotType\n","Architecture\n","Region\n","SubModel\n","Facade\n","State\n","RegionType\n"],"name":"stdout"},{"output_type":"execute_result","data":{"text/html":["
\n","\n","\n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n","
JunkPriceIndex8PriceIndex9PriceIndex7ExpeditedListingPriceIndex4PriceIndex1PriceIndex6ZipInsurancePremiumIndexPriceIndex3PriceIndex5NormalisedPopulationBuildYearPropertyAgePriceIndex2Material_PRN0Material_C8A4Material_ZCI3Material_NYFDAgency_CAT1Agency_CAT2Agency_CAT3Agency_OTHERAreaIncomeType_AAreaIncomeType_BChannel_DirectChannel_OtherChannel_AgentPlotType_WHBIPlotType_W62BPlotType_32T2PlotType_DIJXPlotType_WLQ6Architecture_YIK5Architecture_TP7RArchitecture_I3Z9Architecture_AVYPArchitecture_1M5XRegion_ASubModel_FIVQSubModel_KT8FSubModel_UA42Facade_SILVERFacade_WHITEFacade_BLUEFacade_GREYFacade_BLACKFacade_REDFacade_GOLDState_TXState_FLState_CAState_NCState_AZState_COState_SCRegionType_ARegionType_BRegionType_C
0014674.0827013143.0014224.09217.010387.02107562313108.09022.0420772008210692.000000010011001000000100100000000000000000100
114172.038903461.004404.02958.03400.07312916893695.02742.077258200273615.010000100011001000000010110010000000000000100
208210.059006922.008952.04568.04862.02969723517730.03768.094514200465805.000001000010100100000001100010000000000001100
307309.074606300.007460.05361.06305.02827319336290.05370.082302200276444.000000001100010000100000100001000000001000001
409182.064008330.009846.05428.05718.0296974828583.04803.049176200736286.000000001010101000000000110010000000000001010
\n","
"],"text/plain":[" Junk PriceIndex8 PriceIndex9 ... RegionType_A RegionType_B RegionType_C\n","0 0 14674.0 8270 ... 1 0 0\n","1 1 4172.0 3890 ... 1 0 0\n","2 0 8210.0 5900 ... 1 0 0\n","3 0 7309.0 7460 ... 0 0 1\n","4 0 9182.0 6400 ... 0 1 0\n","\n","[5 rows x 60 columns]"]},"metadata":{"tags":[]},"execution_count":27}]},{"cell_type":"code","metadata":{"id":"Tm8G0nt-TpiJ","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605781243123,"user_tz":-330,"elapsed":1117,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"2a8c5ec8-a16d-4876-c3ff-1c1eda171414"},"source":["print(df.shape)\n","df.dropna(axis=0, inplace=True)\n","print(df.shape)"],"execution_count":28,"outputs":[{"output_type":"stream","text":["(62035, 60)\n","(61763, 60)\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"2Ex8rVfNWUC6","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605781245818,"user_tz":-330,"elapsed":953,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"bd5b3a38-afca-44f6-daa3-0c0bc3d598bc"},"source":["df.shape"],"execution_count":29,"outputs":[{"output_type":"execute_result","data":{"text/plain":["(61763, 60)"]},"metadata":{"tags":[]},"execution_count":29}]},{"cell_type":"code","metadata":{"id":"E67wAhFZbfUX","executionInfo":{"status":"ok","timestamp":1605781247393,"user_tz":-330,"elapsed":1412,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}}},"source":["def report(results, n_top=3):\n"," for i in range(1, n_top + 1):\n"," candidates = np.flatnonzero(results['rank_test_score'] == i)\n"," for candidate in candidates:\n"," print(\"Model with rank: {0}\".format(i))\n"," print(\"Mean validation score: {0:.3f} (std: {1:.5f})\".format(\n"," results['mean_test_score'][candidate],\n"," results['std_test_score'][candidate]))\n"," print(\"Parameters: {0}\".format(results['params'][candidate]))\n"," print(\"\")\n","\n","\n","\n","def grid_search_wrapper(refit_score='recall_score'):\n"," \"\"\"\n"," fits a GridSearchCV classifier using refit_score for optimization\n"," prints classifier performance metrics\n"," \"\"\"\n"," skf = StratifiedKFold(n_splits=10)\n"," grid_search = GridSearchCV(clf, param_grid, scoring=scorers, refit=refit_score,\n"," cv=skf, return_train_score=True, n_jobs=-1, verbose=30)\n"," grid_search.fit(xtrain.values, ytrain.values)\n","\n"," # make the predictions\n"," ypred = grid_search.predict(xtest.values)\n","\n"," print('Best params for {}'.format(refit_score))\n"," print(grid_search.best_params_)\n"," #report(grid_search.cv_results_, n_top=3)\n"," # confusion matrix on the test data.\n"," print('\\nConfusion matrix of Random Forest optimized for {} on the test data:'.format(refit_score))\n"," print(pd.DataFrame(confusion_matrix(ytest, ypred),\n"," columns=['pred_neg', 'pred_pos'], index=['neg', 'pos']))\n"," return grid_search"],"execution_count":30,"outputs":[]},{"cell_type":"code","metadata":{"id":"xQwp9J2IQjNc","executionInfo":{"status":"ok","timestamp":1605785245120,"user_tz":-330,"elapsed":1816,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}}},"source":["xtrain, xtest, ytrain, ytest = train_test_split(df[df.columns[1:]],df.Junk, test_size=0.3, stratify=df.Junk)\n"],"execution_count":31,"outputs":[]},{"cell_type":"code","metadata":{"id":"_Ci8axLCRxQc","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605777800030,"user_tz":-330,"elapsed":6001303,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"68337d12-1fd7-48de-caca-d7df1e51e8b4"},"source":["\n","#deciding Beta value for model :\n","\n","clf = RandomForestClassifier()\n","param_grid = {\n"," \"class_weight\":[{1:0.122,0:0.877}],\n"," \"n_estimators\":[500],\n"," #'min_samples_split': [3, 5, 10], \n"," #'max_depth': [10, 20, 30],\n"," #'max_features': [3, 5, 10, 20]\n","}\n","\n","for beta_val in {0.5,0.7,1,1.5,2,5,10,20,40,70,90}:\n"," scorers = {\n"," 'precision_score': make_scorer(precision_score),\n"," 'recall_score': make_scorer(recall_score),\n"," 'accuracy_score': make_scorer(accuracy_score),\n"," 'fbeta_score': make_scorer(fbeta_score, beta=beta_val)\n"," }\n"," print('*********************************************************************************')\n"," print('__________________________________',beta_val,'________________________________________')\n"," grid_search_clf = grid_search_wrapper(refit_score='fbeta_score')\n"," print('*********************************************************************************') \n"],"execution_count":14,"outputs":[{"output_type":"stream","text":["*********************************************************************************\n","__________________________________ 0.5 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.2min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.3min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16165 92\n","pos 1821 451\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 0.7 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.2min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.3min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16161 96\n","pos 1825 447\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 2 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.2min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.3min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16166 91\n","pos 1826 446\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 1 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.6min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.6min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.2min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.2min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.7min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.7min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16168 89\n","pos 1831 441\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 1.5 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.6min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.6min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.2min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.2min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.7min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.7min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16170 87\n","pos 1828 444\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 5 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.3min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.4min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.0min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.0min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16161 96\n","pos 1834 438\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 70 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.8min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.8min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.4min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.4min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.0min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.0min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16164 93\n","pos 1827 445\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 40 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.8min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.3min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.4min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.9min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.9min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16170 87\n","pos 1827 445\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 10 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.3min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.3min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.9min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.9min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.5min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.5min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.1min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.1min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16169 88\n","pos 1828 444\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 20 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.3min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.3min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.9min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.9min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.4min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.5min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.0min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.0min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16170 87\n","pos 1845 427\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 90 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.8min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.3min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.4min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.0min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.0min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16169 88\n","pos 1819 453\n","*********************************************************************************\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"g-Qo5k-SqRd3","executionInfo":{"status":"ok","timestamp":1605710875910,"user_tz":-330,"elapsed":2706193,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"ad9e639c-d1a5-4002-ff28-f841d570a18f"},"source":["for beta_val in {200,500,1000,1500,2000}:\n"," scorers = {\n"," 'precision_score': make_scorer(precision_score),\n"," 'recall_score': make_scorer(recall_score),\n"," 'accuracy_score': make_scorer(accuracy_score),\n"," 'fbeta_score': make_scorer(fbeta_score, beta=beta_val)\n"," }\n"," print('*********************************************************************************')\n"," print('__________________________________',beta_val,'________________________________________')\n"," grid_search_clf = grid_search_wrapper(refit_score='fbeta_score')\n"," print('*********************************************************************************')"],"execution_count":44,"outputs":[{"output_type":"stream","text":["*********************************************************************************\n","__________________________________ 200 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.3min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.3min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16132 125\n","pos 1817 455\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 1000 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.8min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.3min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.3min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16145 112\n","pos 1837 435\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 2000 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.8min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.3min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.3min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.9min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.9min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16133 124\n","pos 1843 429\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 500 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.3min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.3min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.9min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.9min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16144 113\n","pos 1828 444\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 1500 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.6min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.2min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.3min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.9min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.9min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16132 125\n","pos 1830 442\n","*********************************************************************************\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"nGA3Aptg8ZEj","executionInfo":{"status":"ok","timestamp":1605714927583,"user_tz":-330,"elapsed":1771485,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"f80068a6-90d7-40d0-b4bf-eab35bb6f4da"},"source":["from xgboost import XGBClassifier\n","clf = XGBClassifier()\n","\n","param_grid = {\n"," 'learning_rate': [0.9],\n"," 'class_weight': [{1: 0.122, 0: 0.877}], 'n_estimators': [500],\n"," #'max_depth': [3, 5, 7, 10,15]\n"," #'min_child_weight': [1, 3, 5],\n"," #'subsample': [0.5, 0.7],\n"," #'colsample_bytree': [0.5, 0.7]\n","}\n","\n","for beta_val in {0,1,100,200,500,1000}:\n"," scorers = {\n"," 'precision_score': make_scorer(precision_score),\n"," 'recall_score': make_scorer(recall_score),\n"," 'accuracy_score': make_scorer(accuracy_score),\n"," 'fbeta_score': make_scorer(fbeta_score, beta=beta_val)\n"," }\n"," print('*********************************************************************************')\n"," print('__________________________________',beta_val,'________________________________________')\n"," grid_search_clf = grid_search_wrapper(refit_score='fbeta_score')\n"," print('*********************************************************************************')"],"execution_count":46,"outputs":[{"output_type":"stream","text":["*********************************************************************************\n","__________________________________ 0 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 52.6s\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 52.7s\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 3.4min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 3.4min remaining: 51.7s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.3min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.3min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 15686 571\n","pos 1691 581\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 1 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 55.0s\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 55.1s\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 1.8min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 1.8min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 3.5min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 3.5min remaining: 52.5s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.4min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.4min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 15686 571\n","pos 1691 581\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 100 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 51.5s\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 51.5s\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 3.4min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 3.4min remaining: 51.7s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.3min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.3min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 15686 571\n","pos 1691 581\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 200 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 55.1s\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 55.3s\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 1.8min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 1.8min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 3.5min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 3.5min remaining: 52.5s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.4min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.4min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 15686 571\n","pos 1691 581\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 1000 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 51.7s\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 51.8s\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 3.4min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 3.4min remaining: 51.5s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.3min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.3min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 15686 571\n","pos 1691 581\n","*********************************************************************************\n","*********************************************************************************\n","__________________________________ 500 ________________________________________\n","Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 51.3s\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 51.4s\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 1.7min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 3.5min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 3.5min remaining: 52.4s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.3min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 4.3min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 15686 571\n","pos 1691 581\n","*********************************************************************************\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"XNTy31JXIsWv","executionInfo":{"status":"ok","timestamp":1605785343775,"user_tz":-330,"elapsed":1181,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}}},"source":["scorers = {\n"," 'precision_score': make_scorer(precision_score),\n"," 'recall_score': make_scorer(recall_score),\n"," 'accuracy_score': make_scorer(accuracy_score),\n"," 'fbeta_score': make_scorer(fbeta_score, beta=200),\n"," 'roc_auc_score':make_scorer(roc_auc_score)\n","}\n","from sklearn.model_selection import RandomizedSearchCV\n","from sklearn.tree import DecisionTreeClassifier\n","from sklearn.ensemble import RandomForestClassifier\n","\n"],"execution_count":32,"outputs":[]},{"cell_type":"code","metadata":{"id":"8e_zLiZ7SJec","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605694532969,"user_tz":-330,"elapsed":556557,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"a30eeca4-18e9-4ba5-c6aa-b2fe306217c5"},"source":["clf = RandomForestClassifier()\n","param_grid = {\n"," \"class_weight\":[{1:0.122,0:0.877}],\n"," \"n_estimators\":[500],\n"," #'min_samples_split': [3, 5, 10], \n"," #'max_depth': [3, 5, 15, 25],\n"," #'max_features': [3, 5, 10, 20]\n","}\n","grid_search_clf = grid_search_wrapper(refit_score='precision_score')\n"],"execution_count":20,"outputs":[{"output_type":"stream","text":["Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.2min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.7min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.8min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.3min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.3min remaining: 1.6min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.0min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 8.0min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for precision_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for precision_score on the test data:\n"," pred_neg pred_pos\n","neg 16133 124\n","pos 1817 455\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"XpOUHlstjwLk","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605212212690,"user_tz":-330,"elapsed":534979,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"791d7d1b-4e84-44f6-e21b-6cb61812570e"},"source":["clf = RandomForestClassifier()\n","param_grid = {\n"," \"class_weight\":[{1:0.122,0:0.877}],\n"," \"n_estimators\":[500],\n"," #'min_samples_split': [3, 5, 10], \n"," #'max_depth': [3, 5, 15, 25],\n"," #'max_features': [3, 5, 10, 20]\n","}\n","grid_search_clf = grid_search_wrapper(refit_score='recall_score')"],"execution_count":null,"outputs":[{"output_type":"stream","text":["Fitting 10 folds for each of 1 candidates, totalling 10 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.1min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.6min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.6min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 6.2min\n","[Parallel(n_jobs=-1)]: Done 8 out of 10 | elapsed: 6.2min remaining: 1.5min\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 10 out of 10 | elapsed: 7.8min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for recall_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for recall_score on the test data:\n"," pred_neg pred_pos\n","neg 16140 117\n","pos 1827 445\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"w5O3F2R40i5F","executionInfo":{"status":"ok","timestamp":1605696690879,"user_tz":-330,"elapsed":1137778,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"7cfb9ec9-29e3-47cf-d098-82cce68ae4eb"},"source":["clf = RandomForestClassifier()\n","param_grid = {\n"," \"class_weight\":[{1:0.122,0:0.877}],\n"," \"n_estimators\":[500],\n"," #'min_samples_split': [3, 5, 10], \n"," 'max_depth': [3, 5, 15, 25],\n"," #'max_features': [3, 5, 10, 20]\n","}\n","grid_search_clf = grid_search_wrapper(refit_score='fbeta_score')"],"execution_count":30,"outputs":[{"output_type":"stream","text":["Fitting 10 folds for each of 4 candidates, totalling 40 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 22.6s\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 22.6s\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 44.3s\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 44.4s\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 1.1min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 1.1min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 8 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 9 tasks | elapsed: 1.8min\n","[Parallel(n_jobs=-1)]: Done 10 tasks | elapsed: 1.8min\n","[Parallel(n_jobs=-1)]: Done 11 tasks | elapsed: 2.3min\n","[Parallel(n_jobs=-1)]: Done 12 tasks | elapsed: 2.4min\n","[Parallel(n_jobs=-1)]: Done 13 tasks | elapsed: 2.8min\n","[Parallel(n_jobs=-1)]: Done 14 tasks | elapsed: 2.9min\n","[Parallel(n_jobs=-1)]: Done 15 tasks | elapsed: 3.4min\n","[Parallel(n_jobs=-1)]: Done 16 tasks | elapsed: 3.4min\n","[Parallel(n_jobs=-1)]: Done 17 tasks | elapsed: 3.9min\n","[Parallel(n_jobs=-1)]: Done 18 tasks | elapsed: 3.9min\n","[Parallel(n_jobs=-1)]: Done 19 tasks | elapsed: 4.4min\n","[Parallel(n_jobs=-1)]: Done 20 tasks | elapsed: 4.4min\n","[Parallel(n_jobs=-1)]: Done 21 tasks | elapsed: 5.5min\n","[Parallel(n_jobs=-1)]: Done 22 tasks | elapsed: 5.5min\n","[Parallel(n_jobs=-1)]: Done 23 tasks | elapsed: 6.7min\n","[Parallel(n_jobs=-1)]: Done 24 tasks | elapsed: 6.7min\n","[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 7.8min\n","[Parallel(n_jobs=-1)]: Done 26 tasks | elapsed: 7.9min\n","[Parallel(n_jobs=-1)]: Done 27 tasks | elapsed: 9.0min\n","[Parallel(n_jobs=-1)]: Done 28 tasks | elapsed: 9.1min\n","[Parallel(n_jobs=-1)]: Done 29 tasks | elapsed: 10.1min\n","[Parallel(n_jobs=-1)]: Done 30 tasks | elapsed: 10.2min\n","[Parallel(n_jobs=-1)]: Done 31 tasks | elapsed: 11.6min\n","[Parallel(n_jobs=-1)]: Done 32 tasks | elapsed: 11.7min\n","[Parallel(n_jobs=-1)]: Done 33 tasks | elapsed: 13.2min\n","[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 13.3min\n","[Parallel(n_jobs=-1)]: Done 35 tasks | elapsed: 14.7min\n","[Parallel(n_jobs=-1)]: Done 36 tasks | elapsed: 14.8min\n","[Parallel(n_jobs=-1)]: Done 37 tasks | elapsed: 16.2min\n","[Parallel(n_jobs=-1)]: Done 40 out of 40 | elapsed: 17.8min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for fbeta_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'max_depth': 25, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for fbeta_score on the test data:\n"," pred_neg pred_pos\n","neg 16183 74\n","pos 1887 385\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"jyggNhpqMfbX","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605785362102,"user_tz":-330,"elapsed":3586,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"df349079-258b-478e-f491-0f694b6da7c7"},"source":["!pip install rfpimp\n","from rfpimp import *\n"],"execution_count":33,"outputs":[{"output_type":"stream","text":["Requirement already satisfied: rfpimp in /usr/local/lib/python3.6/dist-packages (1.3.5)\n","Requirement already satisfied: scikit-learn in /usr/local/lib/python3.6/dist-packages (from rfpimp) (0.22.2.post1)\n","Requirement already satisfied: stratx>=0.2 in /usr/local/lib/python3.6/dist-packages (from rfpimp) (0.5)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.6/dist-packages (from rfpimp) (1.1.4)\n","Requirement already satisfied: matplotlib in /usr/local/lib/python3.6/dist-packages (from rfpimp) (3.2.2)\n","Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from rfpimp) (1.18.5)\n","Requirement already satisfied: scipy>=0.17.0 in /usr/local/lib/python3.6/dist-packages (from scikit-learn->rfpimp) (1.4.1)\n","Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.6/dist-packages (from scikit-learn->rfpimp) (0.17.0)\n","Requirement already satisfied: colour in /usr/local/lib/python3.6/dist-packages (from stratx>=0.2->rfpimp) (0.1.5)\n","Requirement already satisfied: numba in /usr/local/lib/python3.6/dist-packages (from stratx>=0.2->rfpimp) (0.48.0)\n","Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.6/dist-packages (from pandas->rfpimp) (2.8.1)\n","Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.6/dist-packages (from pandas->rfpimp) (2018.9)\n","Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.6/dist-packages (from matplotlib->rfpimp) (0.10.0)\n","Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib->rfpimp) (2.4.7)\n","Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.6/dist-packages (from matplotlib->rfpimp) (1.3.1)\n","Requirement already satisfied: llvmlite<0.32.0,>=0.31.0dev0 in /usr/local/lib/python3.6/dist-packages (from numba->stratx>=0.2->rfpimp) (0.31.0)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.6/dist-packages (from numba->stratx>=0.2->rfpimp) (50.3.2)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.6/dist-packages (from python-dateutil>=2.7.3->pandas->rfpimp) (1.15.0)\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"kdauR-ReqaQm","executionInfo":{"status":"ok","timestamp":1605785529984,"user_tz":-330,"elapsed":855,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}}},"source":["\n","# adding a column in X with random values to help find out correct feature importance and features to be removed.\n","xtrain['random']=np.random.choice(range(xtrain.shape[0]), xtrain.shape[0])\n","xtest['random']=np.random.choice(range(xtrain.shape[0]), xtest.shape[0])"],"execution_count":35,"outputs":[]},{"cell_type":"code","metadata":{"id":"yip1MQbiRPTb","executionInfo":{"status":"ok","timestamp":1605785534332,"user_tz":-330,"elapsed":873,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}}},"source":["from xgboost import XGBClassifier\n","clf = XGBClassifier()\n","rf=XGBClassifier(base_score=0.5, booster='gbtree',\n"," class_weight={0: 0.877, 1: 0.122}, colsample_bylevel=1,\n"," colsample_bynode=1, colsample_bytree=1, gamma=0,\n"," learning_rate=0.9, max_delta_step=0, max_depth=3,\n"," min_child_weight=1, missing=None, n_estimators=500, n_jobs=1,\n"," nthread=None, objective='binary:logistic', random_state=0,\n"," reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,\n"," silent=None, subsample=1, verbosity=1)"],"execution_count":36,"outputs":[]},{"cell_type":"code","metadata":{"id":"hyylyR-Euo42","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605785538903,"user_tz":-330,"elapsed":848,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"6b5aaa38-f578-422a-f50c-ca212b647b8f"},"source":["xtest.shape"],"execution_count":37,"outputs":[{"output_type":"execute_result","data":{"text/plain":["(18529, 60)"]},"metadata":{"tags":[]},"execution_count":37}]},{"cell_type":"code","metadata":{"id":"67OOYvjFmjEU","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605785577732,"user_tz":-330,"elapsed":38402,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"8a05397b-16ac-4803-e45c-1f4bab7dceb7"},"source":["rf.fit(xtrain, ytrain)"],"execution_count":38,"outputs":[{"output_type":"execute_result","data":{"text/plain":["XGBClassifier(base_score=0.5, booster='gbtree',\n"," class_weight={0: 0.877, 1: 0.122}, colsample_bylevel=1,\n"," colsample_bynode=1, colsample_bytree=1, gamma=0,\n"," learning_rate=0.9, max_delta_step=0, max_depth=3,\n"," min_child_weight=1, missing=None, n_estimators=500, n_jobs=1,\n"," nthread=None, objective='binary:logistic', random_state=0,\n"," reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,\n"," silent=None, subsample=1, verbosity=1)"]},"metadata":{"tags":[]},"execution_count":38}]},{"cell_type":"code","metadata":{"id":"ZSMLkvT7zRfd","executionInfo":{"status":"ok","timestamp":1605785625185,"user_tz":-330,"elapsed":85459,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}}},"source":["list(zip(df.columns,rf.feature_importances_))\n","imp = importances(rf, xtrain, ytrain, n_samples=-1) # this function comes from package rfpimp\n","viz = plot_importances(imp)\n","viz.view()"],"execution_count":39,"outputs":[]},{"cell_type":"code","metadata":{"id":"KMufoOmatljg","colab":{"base_uri":"https://localhost:8080/","height":1000},"executionInfo":{"status":"ok","timestamp":1605785625189,"user_tz":-330,"elapsed":80949,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"08601bc5-14cc-4137-b103-96184e44346c"},"source":["imp"],"execution_count":40,"outputs":[{"output_type":"execute_result","data":{"text/html":["
\n","\n","\n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n","
Importance
Feature
PriceIndex70.133298
PriceIndex60.089860
AreaIncomeType_B0.087801
AreaIncomeType_A0.081140
PriceIndex10.059837
PriceIndex80.050747
PriceIndex50.048804
PriceIndex30.042374
PriceIndex40.040177
PriceIndex20.035435
PriceIndex90.029606
Zip0.022968
NormalisedPopulation0.021025
random0.018365
InsurancePremiumIndex0.015243
PropertyAge0.010940
State_CA0.010617
Channel_Direct0.006407
BuildYear0.004163
State_TX0.001804
Channel_Agent0.001596
PlotType_32T20.001411
Agency_CAT30.001342
State_AZ0.001295
ExpeditedListing0.001203
Agency_CAT20.001156
Agency_CAT10.001018
Channel_Other0.000948
Facade_SILVER0.000902
PlotType_WLQ60.000879
Architecture_YIK50.000833
Material_C8A40.000786
Facade_GREY0.000786
Region_A0.000763
Architecture_AVYP0.000717
Architecture_TP7R0.000694
Material_PRN00.000694
Material_NYFD0.000648
Material_ZCI30.000625
PlotType_WHBI0.000601
Facade_BLUE0.000555
Facade_WHITE0.000532
SubModel_FIVQ0.000486
PlotType_W62B0.000463
Facade_GOLD0.000439
Facade_RED0.000416
State_NC0.000393
RegionType_B0.000393
Architecture_I3Z90.000347
State_SC0.000278
RegionType_C0.000231
PlotType_DIJX0.000231
State_CO0.000162
State_FL0.000162
Architecture_1M5X0.000116
Agency_OTHER0.000093
SubModel_UA420.000023
RegionType_A0.000000
Facade_BLACK-0.000069
SubModel_KT8F-0.000370
\n","
"],"text/plain":[" Importance\n","Feature \n","PriceIndex7 0.133298\n","PriceIndex6 0.089860\n","AreaIncomeType_B 0.087801\n","AreaIncomeType_A 0.081140\n","PriceIndex1 0.059837\n","PriceIndex8 0.050747\n","PriceIndex5 0.048804\n","PriceIndex3 0.042374\n","PriceIndex4 0.040177\n","PriceIndex2 0.035435\n","PriceIndex9 0.029606\n","Zip 0.022968\n","NormalisedPopulation 0.021025\n","random 0.018365\n","InsurancePremiumIndex 0.015243\n","PropertyAge 0.010940\n","State_CA 0.010617\n","Channel_Direct 0.006407\n","BuildYear 0.004163\n","State_TX 0.001804\n","Channel_Agent 0.001596\n","PlotType_32T2 0.001411\n","Agency_CAT3 0.001342\n","State_AZ 0.001295\n","ExpeditedListing 0.001203\n","Agency_CAT2 0.001156\n","Agency_CAT1 0.001018\n","Channel_Other 0.000948\n","Facade_SILVER 0.000902\n","PlotType_WLQ6 0.000879\n","Architecture_YIK5 0.000833\n","Material_C8A4 0.000786\n","Facade_GREY 0.000786\n","Region_A 0.000763\n","Architecture_AVYP 0.000717\n","Architecture_TP7R 0.000694\n","Material_PRN0 0.000694\n","Material_NYFD 0.000648\n","Material_ZCI3 0.000625\n","PlotType_WHBI 0.000601\n","Facade_BLUE 0.000555\n","Facade_WHITE 0.000532\n","SubModel_FIVQ 0.000486\n","PlotType_W62B 0.000463\n","Facade_GOLD 0.000439\n","Facade_RED 0.000416\n","State_NC 0.000393\n","RegionType_B 0.000393\n","Architecture_I3Z9 0.000347\n","State_SC 0.000278\n","RegionType_C 0.000231\n","PlotType_DIJX 0.000231\n","State_CO 0.000162\n","State_FL 0.000162\n","Architecture_1M5X 0.000116\n","Agency_OTHER 0.000093\n","SubModel_UA42 0.000023\n","RegionType_A 0.000000\n","Facade_BLACK -0.000069\n","SubModel_KT8F -0.000370"]},"metadata":{"tags":[]},"execution_count":40}]},{"cell_type":"code","metadata":{"id":"48j5EuDTuHwJ","colab":{"base_uri":"https://localhost:8080/","height":443},"executionInfo":{"status":"ok","timestamp":1605785625193,"user_tz":-330,"elapsed":68399,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"f84bb7d8-d5ba-47db-e003-a9d1eb234a69"},"source":["indx= imp[imp.values > 0.018943].index.values\n","xtrain[indx]"],"execution_count":41,"outputs":[{"output_type":"execute_result","data":{"text/html":["
\n","\n","\n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n","
PriceIndex7PriceIndex6AreaIncomeType_BAreaIncomeType_APriceIndex1PriceIndex8PriceIndex5PriceIndex3PriceIndex4PriceIndex2PriceIndex9ZipNormalisedPopulation
612394434.04910.0103643.05803.03643.04434.05803.04910.041758710584876
228964038.04105.0013276.04933.03276.04038.04933.04105.051807704158119
217705964.03984.0102200.07078.03197.04798.06334.03313.0445029532108042
28599753.09325.0108619.010571.08568.09809.010623.09373.083007413545610
226353633.03778.0013514.04580.02901.04295.05527.04655.051558022981733
..........................................
3079412546.09471.0108586.013669.08411.011953.013553.09735.084357310846078
521654615.04944.0003810.05840.03810.04615.05840.04944.044152827370504
497888597.07292.0103652.010372.05525.07504.08356.04857.041008002253109
115228879.07922.0016743.09606.06167.09401.010349.07696.077308002279501
5596410103.07670.0107308.012064.06411.08393.010029.08823.071952016674014
\n","

43234 rows × 13 columns

\n","
"],"text/plain":[" PriceIndex7 PriceIndex6 ... Zip NormalisedPopulation\n","61239 4434.0 4910.0 ... 87105 84876\n","22896 4038.0 4105.0 ... 77041 58119\n","21770 5964.0 3984.0 ... 29532 108042\n","2859 9753.0 9325.0 ... 74135 45610\n","22635 3633.0 3778.0 ... 80229 81733\n","... ... ... ... ... ...\n","30794 12546.0 9471.0 ... 73108 46078\n","52165 4615.0 4944.0 ... 28273 70504\n","49788 8597.0 7292.0 ... 80022 53109\n","11522 8879.0 7922.0 ... 80022 79501\n","55964 10103.0 7670.0 ... 20166 74014\n","\n","[43234 rows x 13 columns]"]},"metadata":{"tags":[]},"execution_count":41}]},{"cell_type":"code","metadata":{"id":"2KY209RMo9au","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605127919857,"user_tz":-330,"elapsed":1334568,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"9a4525a3-f942-4e30-838c-f5097476bac3"},"source":["from xgboost import XGBClassifier\n","clf = XGBClassifier()\n","\n","param_grid = {\n"," 'learning_rate': [0.01, 0.05,0.1,0.25, 0.5, 0.7],\n"," 'class_weight': [{1: 0.122, 0: 0.877}], 'n_estimators': [500]\n"," #'max_depth': [3, 5, 7, 10],\n"," #'min_child_weight': [1, 3, 5],\n"," #'subsample': [0.5, 0.7],\n"," #'colsample_bytree': [0.5, 0.7]\n","}\n","\n","grid_search_clf = grid_search_wrapper(refit_score='recall_score')\n","\n","gsf= grid_search_clf.best_estimator_\n","gsf.fit(xtrain[indx],ytrain)"],"execution_count":null,"outputs":[{"output_type":"stream","text":["Fitting 10 folds for each of 6 candidates, totalling 60 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 45.3s\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 45.4s\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 2.2min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 2.2min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 2.9min\n","[Parallel(n_jobs=-1)]: Done 8 tasks | elapsed: 2.9min\n","[Parallel(n_jobs=-1)]: Done 9 tasks | elapsed: 3.7min\n","[Parallel(n_jobs=-1)]: Done 10 tasks | elapsed: 3.7min\n","[Parallel(n_jobs=-1)]: Done 11 tasks | elapsed: 4.4min\n","[Parallel(n_jobs=-1)]: Done 12 tasks | elapsed: 4.4min\n","[Parallel(n_jobs=-1)]: Done 13 tasks | elapsed: 5.1min\n","[Parallel(n_jobs=-1)]: Done 14 tasks | elapsed: 5.1min\n","[Parallel(n_jobs=-1)]: Done 15 tasks | elapsed: 5.8min\n","[Parallel(n_jobs=-1)]: Done 16 tasks | elapsed: 5.8min\n","[Parallel(n_jobs=-1)]: Done 17 tasks | elapsed: 6.5min\n","[Parallel(n_jobs=-1)]: Done 18 tasks | elapsed: 6.5min\n","[Parallel(n_jobs=-1)]: Done 19 tasks | elapsed: 7.3min\n","[Parallel(n_jobs=-1)]: Done 20 tasks | elapsed: 7.3min\n","[Parallel(n_jobs=-1)]: Done 21 tasks | elapsed: 8.0min\n","[Parallel(n_jobs=-1)]: Done 22 tasks | elapsed: 8.0min\n","[Parallel(n_jobs=-1)]: Done 23 tasks | elapsed: 8.7min\n","[Parallel(n_jobs=-1)]: Done 24 tasks | elapsed: 8.7min\n","[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 9.4min\n","[Parallel(n_jobs=-1)]: Done 26 tasks | elapsed: 9.4min\n","[Parallel(n_jobs=-1)]: Done 27 tasks | elapsed: 10.1min\n","[Parallel(n_jobs=-1)]: Done 28 tasks | elapsed: 10.1min\n","[Parallel(n_jobs=-1)]: Done 29 tasks | elapsed: 10.8min\n","[Parallel(n_jobs=-1)]: Done 30 tasks | elapsed: 10.9min\n","[Parallel(n_jobs=-1)]: Done 31 tasks | elapsed: 11.6min\n","[Parallel(n_jobs=-1)]: Done 32 tasks | elapsed: 11.6min\n","[Parallel(n_jobs=-1)]: Done 33 tasks | elapsed: 12.3min\n","[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 12.3min\n","[Parallel(n_jobs=-1)]: Done 35 tasks | elapsed: 13.0min\n","[Parallel(n_jobs=-1)]: Done 36 tasks | elapsed: 13.0min\n","[Parallel(n_jobs=-1)]: Done 37 tasks | elapsed: 13.7min\n","[Parallel(n_jobs=-1)]: Done 38 tasks | elapsed: 13.7min\n","[Parallel(n_jobs=-1)]: Done 39 tasks | elapsed: 14.4min\n","[Parallel(n_jobs=-1)]: Done 40 tasks | elapsed: 14.4min\n","[Parallel(n_jobs=-1)]: Done 41 tasks | elapsed: 15.1min\n","[Parallel(n_jobs=-1)]: Done 42 tasks | elapsed: 15.1min\n","[Parallel(n_jobs=-1)]: Done 43 tasks | elapsed: 15.9min\n","[Parallel(n_jobs=-1)]: Done 44 tasks | elapsed: 15.9min\n","[Parallel(n_jobs=-1)]: Done 45 tasks | elapsed: 16.6min\n","[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 16.6min\n","[Parallel(n_jobs=-1)]: Done 47 tasks | elapsed: 17.3min\n","[Parallel(n_jobs=-1)]: Done 48 tasks | elapsed: 17.3min\n","[Parallel(n_jobs=-1)]: Done 49 tasks | elapsed: 18.0min\n","[Parallel(n_jobs=-1)]: Done 50 tasks | elapsed: 18.0min\n","[Parallel(n_jobs=-1)]: Done 51 tasks | elapsed: 18.7min\n","[Parallel(n_jobs=-1)]: Done 52 tasks | elapsed: 18.7min\n","[Parallel(n_jobs=-1)]: Done 53 tasks | elapsed: 19.4min\n","[Parallel(n_jobs=-1)]: Done 54 tasks | elapsed: 19.4min\n","[Parallel(n_jobs=-1)]: Done 55 tasks | elapsed: 20.1min\n","[Parallel(n_jobs=-1)]: Done 56 tasks | elapsed: 20.1min\n","[Parallel(n_jobs=-1)]: Done 57 tasks | elapsed: 20.9min\n","[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 21.6min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 21.6min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for recall_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.7, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for recall_score on the test data:\n"," pred_neg pred_pos\n","neg 15808 449\n","pos 1705 567\n"],"name":"stdout"},{"output_type":"execute_result","data":{"text/plain":["XGBClassifier(base_score=0.5, booster='gbtree',\n"," class_weight={0: 0.877, 1: 0.122}, colsample_bylevel=1,\n"," colsample_bynode=1, colsample_bytree=1, gamma=0,\n"," learning_rate=0.7, max_delta_step=0, max_depth=3,\n"," min_child_weight=1, missing=None, n_estimators=500, n_jobs=1,\n"," nthread=None, objective='binary:logistic', random_state=0,\n"," reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,\n"," silent=None, subsample=1, verbosity=1)"]},"metadata":{"tags":[]},"execution_count":40}]},{"cell_type":"code","metadata":{"id":"Ws0xsVzI1U_k","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605136619634,"user_tz":-330,"elapsed":8532453,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"742f917b-ad25-4f88-9376-d30a7358d1b6"},"source":["from xgboost import XGBClassifier\n","clf = XGBClassifier()\n","\n","param_grid = {\n"," 'learning_rate': [ 0.7,0.9,0.8],\n"," 'class_weight': [{1: 0.122, 0: 0.877}], 'n_estimators': [500],\n"," 'max_depth': [3, 5, 7, 10,15]\n"," #'min_child_weight': [1, 3, 5],\n"," #'subsample': [0.5, 0.7],\n"," #'colsample_bytree': [0.5, 0.7]\n","}\n","\n","grid_search_clf = grid_search_wrapper(refit_score='recall_score')\n","\n","gsf= grid_search_clf.best_estimator_\n","gsf.fit(xtrain[indx],ytrain)\n"],"execution_count":null,"outputs":[{"output_type":"stream","text":["Fitting 10 folds for each of 15 candidates, totalling 150 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 42.9s\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 42.9s\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 1.4min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 1.4min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 2.2min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 2.2min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 2.9min\n","[Parallel(n_jobs=-1)]: Done 8 tasks | elapsed: 2.9min\n","[Parallel(n_jobs=-1)]: Done 9 tasks | elapsed: 3.6min\n","[Parallel(n_jobs=-1)]: Done 10 tasks | elapsed: 3.6min\n","[Parallel(n_jobs=-1)]: Done 11 tasks | elapsed: 4.8min\n","[Parallel(n_jobs=-1)]: Done 12 tasks | elapsed: 4.8min\n","[Parallel(n_jobs=-1)]: Done 13 tasks | elapsed: 6.0min\n","[Parallel(n_jobs=-1)]: Done 14 tasks | elapsed: 6.0min\n","[Parallel(n_jobs=-1)]: Done 15 tasks | elapsed: 7.2min\n","[Parallel(n_jobs=-1)]: Done 16 tasks | elapsed: 7.2min\n","[Parallel(n_jobs=-1)]: Done 17 tasks | elapsed: 8.4min\n","[Parallel(n_jobs=-1)]: Done 18 tasks | elapsed: 8.4min\n","[Parallel(n_jobs=-1)]: Done 19 tasks | elapsed: 9.6min\n","[Parallel(n_jobs=-1)]: Done 20 tasks | elapsed: 9.6min\n","[Parallel(n_jobs=-1)]: Done 21 tasks | elapsed: 11.3min\n","[Parallel(n_jobs=-1)]: Done 22 tasks | elapsed: 11.3min\n","[Parallel(n_jobs=-1)]: Done 23 tasks | elapsed: 13.0min\n","[Parallel(n_jobs=-1)]: Done 24 tasks | elapsed: 13.0min\n","[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 14.7min\n","[Parallel(n_jobs=-1)]: Done 26 tasks | elapsed: 14.7min\n","[Parallel(n_jobs=-1)]: Done 27 tasks | elapsed: 16.4min\n","[Parallel(n_jobs=-1)]: Done 28 tasks | elapsed: 16.4min\n","[Parallel(n_jobs=-1)]: Done 29 tasks | elapsed: 18.1min\n","[Parallel(n_jobs=-1)]: Done 30 tasks | elapsed: 18.1min\n","[Parallel(n_jobs=-1)]: Done 31 tasks | elapsed: 20.6min\n","[Parallel(n_jobs=-1)]: Done 32 tasks | elapsed: 20.6min\n","[Parallel(n_jobs=-1)]: Done 33 tasks | elapsed: 23.0min\n","[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 23.1min\n","[Parallel(n_jobs=-1)]: Done 35 tasks | elapsed: 25.5min\n","[Parallel(n_jobs=-1)]: Done 36 tasks | elapsed: 25.5min\n","[Parallel(n_jobs=-1)]: Done 37 tasks | elapsed: 27.9min\n","[Parallel(n_jobs=-1)]: Done 38 tasks | elapsed: 28.0min\n","[Parallel(n_jobs=-1)]: Done 39 tasks | elapsed: 30.4min\n","[Parallel(n_jobs=-1)]: Done 40 tasks | elapsed: 30.5min\n","[Parallel(n_jobs=-1)]: Done 41 tasks | elapsed: 33.7min\n","[Parallel(n_jobs=-1)]: Done 42 tasks | elapsed: 33.9min\n","[Parallel(n_jobs=-1)]: Done 43 tasks | elapsed: 37.1min\n","[Parallel(n_jobs=-1)]: Done 44 tasks | elapsed: 37.3min\n","[Parallel(n_jobs=-1)]: Done 45 tasks | elapsed: 40.5min\n","[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 40.7min\n","[Parallel(n_jobs=-1)]: Done 47 tasks | elapsed: 44.0min\n","[Parallel(n_jobs=-1)]: Done 48 tasks | elapsed: 44.1min\n","[Parallel(n_jobs=-1)]: Done 49 tasks | elapsed: 47.5min\n","[Parallel(n_jobs=-1)]: Done 50 tasks | elapsed: 47.6min\n","[Parallel(n_jobs=-1)]: Done 51 tasks | elapsed: 48.2min\n","[Parallel(n_jobs=-1)]: Done 52 tasks | elapsed: 48.3min\n","[Parallel(n_jobs=-1)]: Done 53 tasks | elapsed: 49.0min\n","[Parallel(n_jobs=-1)]: Done 54 tasks | elapsed: 49.1min\n","[Parallel(n_jobs=-1)]: Done 55 tasks | elapsed: 49.7min\n","[Parallel(n_jobs=-1)]: Done 56 tasks | elapsed: 49.8min\n","[Parallel(n_jobs=-1)]: Done 57 tasks | elapsed: 50.4min\n","[Parallel(n_jobs=-1)]: Done 58 tasks | elapsed: 50.6min\n","[Parallel(n_jobs=-1)]: Done 59 tasks | elapsed: 51.2min\n","[Parallel(n_jobs=-1)]: Done 60 tasks | elapsed: 51.3min\n","[Parallel(n_jobs=-1)]: Done 61 tasks | elapsed: 52.4min\n","[Parallel(n_jobs=-1)]: Done 62 tasks | elapsed: 52.5min\n","[Parallel(n_jobs=-1)]: Done 63 tasks | elapsed: 53.6min\n","[Parallel(n_jobs=-1)]: Done 64 tasks | elapsed: 53.8min\n","[Parallel(n_jobs=-1)]: Done 65 tasks | elapsed: 54.9min\n","[Parallel(n_jobs=-1)]: Done 66 tasks | elapsed: 55.0min\n","[Parallel(n_jobs=-1)]: Done 67 tasks | elapsed: 56.1min\n","[Parallel(n_jobs=-1)]: Done 68 tasks | elapsed: 56.2min\n","[Parallel(n_jobs=-1)]: Done 69 tasks | elapsed: 57.3min\n","[Parallel(n_jobs=-1)]: Done 70 tasks | elapsed: 57.4min\n","[Parallel(n_jobs=-1)]: Done 71 tasks | elapsed: 59.1min\n","[Parallel(n_jobs=-1)]: Done 72 tasks | elapsed: 59.2min\n","[Parallel(n_jobs=-1)]: Done 73 tasks | elapsed: 60.8min\n","[Parallel(n_jobs=-1)]: Done 74 tasks | elapsed: 60.9min\n","[Parallel(n_jobs=-1)]: Done 75 tasks | elapsed: 62.5min\n","[Parallel(n_jobs=-1)]: Done 76 tasks | elapsed: 62.7min\n","[Parallel(n_jobs=-1)]: Done 77 tasks | elapsed: 64.3min\n","[Parallel(n_jobs=-1)]: Done 78 tasks | elapsed: 64.4min\n","[Parallel(n_jobs=-1)]: Done 79 tasks | elapsed: 66.0min\n","[Parallel(n_jobs=-1)]: Done 80 tasks | elapsed: 66.2min\n","[Parallel(n_jobs=-1)]: Done 81 tasks | elapsed: 68.5min\n","[Parallel(n_jobs=-1)]: Done 82 tasks | elapsed: 68.7min\n","[Parallel(n_jobs=-1)]: Done 83 tasks | elapsed: 71.0min\n","[Parallel(n_jobs=-1)]: Done 84 tasks | elapsed: 71.2min\n","[Parallel(n_jobs=-1)]: Done 85 tasks | elapsed: 73.5min\n","[Parallel(n_jobs=-1)]: Done 86 tasks | elapsed: 73.7min\n","[Parallel(n_jobs=-1)]: Done 87 tasks | elapsed: 76.0min\n","[Parallel(n_jobs=-1)]: Done 88 tasks | elapsed: 76.2min\n","[Parallel(n_jobs=-1)]: Done 89 tasks | elapsed: 78.5min\n","[Parallel(n_jobs=-1)]: Done 90 tasks | elapsed: 78.7min\n","[Parallel(n_jobs=-1)]: Done 91 tasks | elapsed: 81.7min\n","[Parallel(n_jobs=-1)]: Done 92 tasks | elapsed: 81.9min\n","[Parallel(n_jobs=-1)]: Done 93 tasks | elapsed: 84.8min\n","[Parallel(n_jobs=-1)]: Done 94 tasks | elapsed: 85.0min\n","[Parallel(n_jobs=-1)]: Done 95 tasks | elapsed: 88.0min\n","[Parallel(n_jobs=-1)]: Done 96 tasks | elapsed: 88.2min\n","[Parallel(n_jobs=-1)]: Done 97 tasks | elapsed: 91.2min\n","[Parallel(n_jobs=-1)]: Done 98 tasks | elapsed: 91.4min\n","[Parallel(n_jobs=-1)]: Done 99 tasks | elapsed: 94.3min\n","[Parallel(n_jobs=-1)]: Done 100 tasks | elapsed: 94.6min\n","[Parallel(n_jobs=-1)]: Done 101 tasks | elapsed: 95.1min\n","[Parallel(n_jobs=-1)]: Done 102 tasks | elapsed: 95.3min\n","[Parallel(n_jobs=-1)]: Done 103 tasks | elapsed: 95.8min\n","[Parallel(n_jobs=-1)]: Done 104 tasks | elapsed: 96.0min\n","[Parallel(n_jobs=-1)]: Done 105 tasks | elapsed: 96.5min\n","[Parallel(n_jobs=-1)]: Done 106 tasks | elapsed: 96.8min\n","[Parallel(n_jobs=-1)]: Done 107 tasks | elapsed: 97.2min\n","[Parallel(n_jobs=-1)]: Done 108 tasks | elapsed: 97.5min\n","[Parallel(n_jobs=-1)]: Done 109 tasks | elapsed: 98.0min\n","[Parallel(n_jobs=-1)]: Done 110 tasks | elapsed: 98.2min\n","[Parallel(n_jobs=-1)]: Done 111 tasks | elapsed: 99.2min\n","[Parallel(n_jobs=-1)]: Done 112 tasks | elapsed: 99.4min\n","[Parallel(n_jobs=-1)]: Done 113 tasks | elapsed: 100.4min\n","[Parallel(n_jobs=-1)]: Done 114 tasks | elapsed: 100.6min\n","[Parallel(n_jobs=-1)]: Done 115 tasks | elapsed: 101.6min\n","[Parallel(n_jobs=-1)]: Done 116 tasks | elapsed: 101.8min\n","[Parallel(n_jobs=-1)]: Done 117 tasks | elapsed: 102.8min\n","[Parallel(n_jobs=-1)]: Done 118 tasks | elapsed: 103.0min\n","[Parallel(n_jobs=-1)]: Done 119 tasks | elapsed: 104.0min\n","[Parallel(n_jobs=-1)]: Done 120 tasks | elapsed: 104.2min\n","[Parallel(n_jobs=-1)]: Done 121 tasks | elapsed: 105.6min\n","[Parallel(n_jobs=-1)]: Done 122 tasks | elapsed: 105.9min\n","[Parallel(n_jobs=-1)]: Done 123 tasks | elapsed: 107.3min\n","[Parallel(n_jobs=-1)]: Done 124 tasks | elapsed: 107.6min\n","[Parallel(n_jobs=-1)]: Done 125 tasks | elapsed: 109.1min\n","[Parallel(n_jobs=-1)]: Done 126 tasks | elapsed: 109.3min\n","[Parallel(n_jobs=-1)]: Done 127 tasks | elapsed: 110.8min\n","[Parallel(n_jobs=-1)]: Done 128 tasks | elapsed: 111.0min\n","[Parallel(n_jobs=-1)]: Done 129 tasks | elapsed: 112.4min\n","[Parallel(n_jobs=-1)]: Done 130 tasks | elapsed: 112.7min\n","[Parallel(n_jobs=-1)]: Done 131 tasks | elapsed: 114.9min\n","[Parallel(n_jobs=-1)]: Done 132 tasks | elapsed: 115.2min\n","[Parallel(n_jobs=-1)]: Done 133 tasks | elapsed: 117.3min\n","[Parallel(n_jobs=-1)]: Done 134 tasks | elapsed: 117.6min\n","[Parallel(n_jobs=-1)]: Done 135 tasks | elapsed: 119.8min\n","[Parallel(n_jobs=-1)]: Done 136 tasks | elapsed: 120.1min\n","[Parallel(n_jobs=-1)]: Done 137 tasks | elapsed: 122.2min\n","[Parallel(n_jobs=-1)]: Done 138 tasks | elapsed: 122.5min\n","[Parallel(n_jobs=-1)]: Done 139 tasks | elapsed: 124.7min\n","[Parallel(n_jobs=-1)]: Done 140 tasks | elapsed: 125.0min\n","[Parallel(n_jobs=-1)]: Done 141 tasks | elapsed: 127.9min\n","[Parallel(n_jobs=-1)]: Done 142 tasks | elapsed: 128.2min\n","[Parallel(n_jobs=-1)]: Done 143 tasks | elapsed: 131.2min\n","[Parallel(n_jobs=-1)]: Done 144 tasks | elapsed: 131.5min\n","[Parallel(n_jobs=-1)]: Done 145 tasks | elapsed: 134.4min\n","[Parallel(n_jobs=-1)]: Done 146 tasks | elapsed: 134.7min\n","[Parallel(n_jobs=-1)]: Done 147 tasks | elapsed: 137.7min\n","[Parallel(n_jobs=-1)]: Done 150 out of 150 | elapsed: 141.1min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for recall_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'max_depth': 5, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for recall_score on the test data:\n"," pred_neg pred_pos\n","neg 15631 626\n","pos 1673 599\n"],"name":"stdout"},{"output_type":"execute_result","data":{"text/plain":["XGBClassifier(base_score=0.5, booster='gbtree',\n"," class_weight={0: 0.877, 1: 0.122}, colsample_bylevel=1,\n"," colsample_bynode=1, colsample_bytree=1, gamma=0,\n"," learning_rate=0.9, max_delta_step=0, max_depth=5,\n"," min_child_weight=1, missing=None, n_estimators=500, n_jobs=1,\n"," nthread=None, objective='binary:logistic', random_state=0,\n"," reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,\n"," silent=None, subsample=1, verbosity=1)"]},"metadata":{"tags":[]},"execution_count":41}]},{"cell_type":"code","metadata":{"id":"UcosObcqCVLL","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605216837249,"user_tz":-330,"elapsed":4624389,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"aa68ea90-fa18-42a2-b5b2-b1c7bde401e3"},"source":["from xgboost import XGBClassifier\n","clf = XGBClassifier()\n","\n","param_grid = {\n"," 'learning_rate': [ 0.9],\n"," 'class_weight': [{1: 0.122, 0: 0.877}], 'n_estimators': [500],\n"," 'max_depth': [5],\n"," 'min_child_weight': [1, 3, 5,10,15,50,100,75,125]\n"," #'subsample': [0.5, 0.7],\n"," #'colsample_bytree': [0.5, 0.7]\n","}\n","\n","grid_search_clf = grid_search_wrapper(refit_score='recall_score')\n","\n","gsf= grid_search_clf.best_estimator_\n","gsf.fit(xtrain[indx],ytrain)"],"execution_count":null,"outputs":[{"output_type":"stream","text":["Fitting 10 folds for each of 9 candidates, totalling 90 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.5min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 3.0min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 3.0min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.4min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.4min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 5.9min\n","[Parallel(n_jobs=-1)]: Done 8 tasks | elapsed: 5.9min\n","[Parallel(n_jobs=-1)]: Done 9 tasks | elapsed: 7.3min\n","[Parallel(n_jobs=-1)]: Done 10 tasks | elapsed: 7.3min\n","[Parallel(n_jobs=-1)]: Done 11 tasks | elapsed: 8.7min\n","[Parallel(n_jobs=-1)]: Done 12 tasks | elapsed: 8.8min\n","[Parallel(n_jobs=-1)]: Done 13 tasks | elapsed: 10.2min\n","[Parallel(n_jobs=-1)]: Done 14 tasks | elapsed: 10.2min\n","[Parallel(n_jobs=-1)]: Done 15 tasks | elapsed: 11.6min\n","[Parallel(n_jobs=-1)]: Done 16 tasks | elapsed: 11.6min\n","[Parallel(n_jobs=-1)]: Done 17 tasks | elapsed: 13.0min\n","[Parallel(n_jobs=-1)]: Done 18 tasks | elapsed: 13.1min\n","[Parallel(n_jobs=-1)]: Done 19 tasks | elapsed: 14.5min\n","[Parallel(n_jobs=-1)]: Done 20 tasks | elapsed: 14.5min\n","[Parallel(n_jobs=-1)]: Done 21 tasks | elapsed: 15.9min\n","[Parallel(n_jobs=-1)]: Done 22 tasks | elapsed: 15.9min\n","[Parallel(n_jobs=-1)]: Done 23 tasks | elapsed: 17.3min\n","[Parallel(n_jobs=-1)]: Done 24 tasks | elapsed: 17.3min\n","[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 18.7min\n","[Parallel(n_jobs=-1)]: Done 26 tasks | elapsed: 18.8min\n","[Parallel(n_jobs=-1)]: Done 27 tasks | elapsed: 20.2min\n","[Parallel(n_jobs=-1)]: Done 28 tasks | elapsed: 20.2min\n","[Parallel(n_jobs=-1)]: Done 29 tasks | elapsed: 21.6min\n","[Parallel(n_jobs=-1)]: Done 30 tasks | elapsed: 21.7min\n","[Parallel(n_jobs=-1)]: Done 31 tasks | elapsed: 23.0min\n","[Parallel(n_jobs=-1)]: Done 32 tasks | elapsed: 23.1min\n","[Parallel(n_jobs=-1)]: Done 33 tasks | elapsed: 24.4min\n","[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 24.5min\n","[Parallel(n_jobs=-1)]: Done 35 tasks | elapsed: 25.8min\n","[Parallel(n_jobs=-1)]: Done 36 tasks | elapsed: 25.9min\n","[Parallel(n_jobs=-1)]: Done 37 tasks | elapsed: 27.2min\n","[Parallel(n_jobs=-1)]: Done 38 tasks | elapsed: 27.3min\n","[Parallel(n_jobs=-1)]: Done 39 tasks | elapsed: 28.7min\n","[Parallel(n_jobs=-1)]: Done 40 tasks | elapsed: 28.8min\n","[Parallel(n_jobs=-1)]: Done 41 tasks | elapsed: 30.1min\n","[Parallel(n_jobs=-1)]: Done 42 tasks | elapsed: 30.2min\n","[Parallel(n_jobs=-1)]: Done 43 tasks | elapsed: 31.5min\n","[Parallel(n_jobs=-1)]: Done 44 tasks | elapsed: 31.6min\n","[Parallel(n_jobs=-1)]: Done 45 tasks | elapsed: 32.9min\n","[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 33.0min\n","[Parallel(n_jobs=-1)]: Done 47 tasks | elapsed: 34.3min\n","[Parallel(n_jobs=-1)]: Done 48 tasks | elapsed: 34.4min\n","[Parallel(n_jobs=-1)]: Done 49 tasks | elapsed: 35.7min\n","[Parallel(n_jobs=-1)]: Done 50 tasks | elapsed: 35.9min\n","[Parallel(n_jobs=-1)]: Done 51 tasks | elapsed: 37.1min\n","[Parallel(n_jobs=-1)]: Done 52 tasks | elapsed: 37.3min\n","[Parallel(n_jobs=-1)]: Done 53 tasks | elapsed: 38.6min\n","[Parallel(n_jobs=-1)]: Done 54 tasks | elapsed: 38.7min\n","[Parallel(n_jobs=-1)]: Done 55 tasks | elapsed: 40.0min\n","[Parallel(n_jobs=-1)]: Done 56 tasks | elapsed: 40.1min\n","[Parallel(n_jobs=-1)]: Done 57 tasks | elapsed: 41.4min\n","[Parallel(n_jobs=-1)]: Done 58 tasks | elapsed: 41.5min\n","[Parallel(n_jobs=-1)]: Done 59 tasks | elapsed: 42.8min\n","[Parallel(n_jobs=-1)]: Done 60 tasks | elapsed: 42.9min\n","[Parallel(n_jobs=-1)]: Done 61 tasks | elapsed: 44.4min\n","[Parallel(n_jobs=-1)]: Done 62 tasks | elapsed: 44.5min\n","[Parallel(n_jobs=-1)]: Done 63 tasks | elapsed: 46.1min\n","[Parallel(n_jobs=-1)]: Done 64 tasks | elapsed: 46.3min\n","[Parallel(n_jobs=-1)]: Done 65 tasks | elapsed: 47.7min\n","[Parallel(n_jobs=-1)]: Done 66 tasks | elapsed: 47.9min\n","[Parallel(n_jobs=-1)]: Done 67 tasks | elapsed: 49.3min\n","[Parallel(n_jobs=-1)]: Done 68 tasks | elapsed: 49.5min\n","[Parallel(n_jobs=-1)]: Done 69 tasks | elapsed: 51.3min\n","[Parallel(n_jobs=-1)]: Done 70 tasks | elapsed: 51.5min\n","[Parallel(n_jobs=-1)]: Done 71 tasks | elapsed: 53.0min\n","[Parallel(n_jobs=-1)]: Done 72 tasks | elapsed: 53.2min\n","[Parallel(n_jobs=-1)]: Done 73 tasks | elapsed: 54.5min\n","[Parallel(n_jobs=-1)]: Done 74 tasks | elapsed: 54.6min\n","[Parallel(n_jobs=-1)]: Done 75 tasks | elapsed: 55.9min\n","[Parallel(n_jobs=-1)]: Done 76 tasks | elapsed: 56.1min\n","[Parallel(n_jobs=-1)]: Done 77 tasks | elapsed: 57.6min\n","[Parallel(n_jobs=-1)]: Done 78 tasks | elapsed: 57.8min\n","[Parallel(n_jobs=-1)]: Done 79 tasks | elapsed: 59.3min\n","[Parallel(n_jobs=-1)]: Done 80 tasks | elapsed: 59.5min\n","[Parallel(n_jobs=-1)]: Done 81 tasks | elapsed: 60.8min\n","[Parallel(n_jobs=-1)]: Done 82 tasks | elapsed: 61.0min\n","[Parallel(n_jobs=-1)]: Done 83 tasks | elapsed: 62.4min\n","[Parallel(n_jobs=-1)]: Done 84 tasks | elapsed: 62.7min\n","[Parallel(n_jobs=-1)]: Done 85 tasks | elapsed: 64.2min\n","[Parallel(n_jobs=-1)]: Done 86 tasks | elapsed: 64.5min\n","[Parallel(n_jobs=-1)]: Done 87 tasks | elapsed: 65.9min\n","[Parallel(n_jobs=-1)]: Done 90 out of 90 | elapsed: 67.5min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for recall_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'max_depth': 5, 'min_child_weight': 10, 'n_estimators': 500}\n","\n","Confusion matrix of Random Forest optimized for recall_score on the test data:\n"," pred_neg pred_pos\n","neg 15612 645\n","pos 1647 625\n"],"name":"stdout"},{"output_type":"execute_result","data":{"text/plain":["XGBClassifier(base_score=0.5, booster='gbtree',\n"," class_weight={0: 0.877, 1: 0.122}, colsample_bylevel=1,\n"," colsample_bynode=1, colsample_bytree=1, gamma=0,\n"," learning_rate=0.9, max_delta_step=0, max_depth=5,\n"," min_child_weight=10, missing=None, n_estimators=500, n_jobs=1,\n"," nthread=None, objective='binary:logistic', random_state=0,\n"," reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,\n"," silent=None, subsample=1, verbosity=1)"]},"metadata":{"tags":[]},"execution_count":23}]},{"cell_type":"code","metadata":{"id":"llg5FJjVhYeb","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605220035098,"user_tz":-330,"elapsed":2874303,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"14766729-0900-4eae-b54f-ef84293c78df"},"source":["from xgboost import XGBClassifier\n","clf = XGBClassifier()\n","\n","param_grid = {\n"," 'learning_rate': [ 0.9],\n"," 'class_weight': [{1: 0.122, 0: 0.877}], 'n_estimators': [500],\n"," 'max_depth': [5],\n"," 'min_child_weight': [10],\n"," 'subsample': [0.2,0.3,0.5,0.6, 0.7,0.9],\n"," #'colsample_bytree': [0.5, 0.7]\n","}\n","\n","grid_search_clf = grid_search_wrapper(refit_score='recall_score')\n","\n","gsf= grid_search_clf.best_estimator_\n","gsf.fit(xtrain[indx],ytrain)"],"execution_count":null,"outputs":[{"output_type":"stream","text":["Fitting 10 folds for each of 6 candidates, totalling 60 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.2min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.2min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 2.3min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 2.3min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 3.4min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 3.4min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 4.6min\n","[Parallel(n_jobs=-1)]: Done 8 tasks | elapsed: 4.6min\n","[Parallel(n_jobs=-1)]: Done 9 tasks | elapsed: 5.7min\n","[Parallel(n_jobs=-1)]: Done 10 tasks | elapsed: 5.7min\n","[Parallel(n_jobs=-1)]: Done 11 tasks | elapsed: 7.1min\n","[Parallel(n_jobs=-1)]: Done 12 tasks | elapsed: 7.1min\n","[Parallel(n_jobs=-1)]: Done 13 tasks | elapsed: 8.4min\n","[Parallel(n_jobs=-1)]: Done 14 tasks | elapsed: 8.5min\n","[Parallel(n_jobs=-1)]: Done 15 tasks | elapsed: 9.8min\n","[Parallel(n_jobs=-1)]: Done 16 tasks | elapsed: 9.8min\n","[Parallel(n_jobs=-1)]: Done 17 tasks | elapsed: 11.2min\n","[Parallel(n_jobs=-1)]: Done 18 tasks | elapsed: 11.2min\n","[Parallel(n_jobs=-1)]: Done 19 tasks | elapsed: 12.5min\n","[Parallel(n_jobs=-1)]: Done 20 tasks | elapsed: 12.6min\n","[Parallel(n_jobs=-1)]: Done 21 tasks | elapsed: 14.3min\n","[Parallel(n_jobs=-1)]: Done 22 tasks | elapsed: 14.4min\n","[Parallel(n_jobs=-1)]: Done 23 tasks | elapsed: 16.0min\n","[Parallel(n_jobs=-1)]: Done 24 tasks | elapsed: 16.1min\n","[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 17.7min\n","[Parallel(n_jobs=-1)]: Done 26 tasks | elapsed: 17.8min\n","[Parallel(n_jobs=-1)]: Done 27 tasks | elapsed: 19.4min\n","[Parallel(n_jobs=-1)]: Done 28 tasks | elapsed: 19.5min\n","[Parallel(n_jobs=-1)]: Done 29 tasks | elapsed: 21.1min\n","[Parallel(n_jobs=-1)]: Done 30 tasks | elapsed: 21.3min\n","[Parallel(n_jobs=-1)]: Done 31 tasks | elapsed: 22.9min\n","[Parallel(n_jobs=-1)]: Done 32 tasks | elapsed: 23.0min\n","[Parallel(n_jobs=-1)]: Done 33 tasks | elapsed: 24.7min\n","[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 24.8min\n","[Parallel(n_jobs=-1)]: Done 35 tasks | elapsed: 26.4min\n","[Parallel(n_jobs=-1)]: Done 36 tasks | elapsed: 26.6min\n","[Parallel(n_jobs=-1)]: Done 37 tasks | elapsed: 28.2min\n","[Parallel(n_jobs=-1)]: Done 38 tasks | elapsed: 28.3min\n","[Parallel(n_jobs=-1)]: Done 39 tasks | elapsed: 29.9min\n","[Parallel(n_jobs=-1)]: Done 40 tasks | elapsed: 30.1min\n","[Parallel(n_jobs=-1)]: Done 41 tasks | elapsed: 31.6min\n","[Parallel(n_jobs=-1)]: Done 42 tasks | elapsed: 31.8min\n","[Parallel(n_jobs=-1)]: Done 43 tasks | elapsed: 33.3min\n","[Parallel(n_jobs=-1)]: Done 44 tasks | elapsed: 33.5min\n","[Parallel(n_jobs=-1)]: Done 45 tasks | elapsed: 35.0min\n","[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 35.3min\n","[Parallel(n_jobs=-1)]: Done 47 tasks | elapsed: 36.7min\n","[Parallel(n_jobs=-1)]: Done 48 tasks | elapsed: 37.0min\n","[Parallel(n_jobs=-1)]: Done 49 tasks | elapsed: 38.4min\n","[Parallel(n_jobs=-1)]: Done 50 tasks | elapsed: 38.7min\n","[Parallel(n_jobs=-1)]: Done 51 tasks | elapsed: 39.9min\n","[Parallel(n_jobs=-1)]: Done 52 tasks | elapsed: 40.2min\n","[Parallel(n_jobs=-1)]: Done 53 tasks | elapsed: 41.5min\n","[Parallel(n_jobs=-1)]: Done 54 tasks | elapsed: 41.8min\n","[Parallel(n_jobs=-1)]: Done 55 tasks | elapsed: 43.0min\n","[Parallel(n_jobs=-1)]: Done 56 tasks | elapsed: 43.3min\n","[Parallel(n_jobs=-1)]: Done 57 tasks | elapsed: 44.6min\n","[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 46.4min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 46.4min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for recall_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'max_depth': 5, 'min_child_weight': 10, 'n_estimators': 500, 'subsample': 0.3}\n","\n","Confusion matrix of Random Forest optimized for recall_score on the test data:\n"," pred_neg pred_pos\n","neg 14653 1604\n","pos 1641 631\n"],"name":"stdout"},{"output_type":"execute_result","data":{"text/plain":["XGBClassifier(base_score=0.5, booster='gbtree',\n"," class_weight={0: 0.877, 1: 0.122}, colsample_bylevel=1,\n"," colsample_bynode=1, colsample_bytree=1, gamma=0,\n"," learning_rate=0.9, max_delta_step=0, max_depth=5,\n"," min_child_weight=10, missing=None, n_estimators=500, n_jobs=1,\n"," nthread=None, objective='binary:logistic', random_state=0,\n"," reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,\n"," silent=None, subsample=0.3, verbosity=1)"]},"metadata":{"tags":[]},"execution_count":25}]},{"cell_type":"code","metadata":{"id":"coxgSVuJj3td","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605222968151,"user_tz":-330,"elapsed":2536575,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"8216e3b1-2fe8-49c6-c7df-7ac70ef22e4f"},"source":["from xgboost import XGBClassifier\n","clf = XGBClassifier()\n","\n","param_grid = {\n"," 'learning_rate': [ 0.9],\n"," 'class_weight': [{1: 0.122, 0: 0.877}], 'n_estimators': [500],\n"," 'max_depth': [5],\n"," 'min_child_weight': [10],\n"," 'subsample': [0.3],\n"," 'scale_pos_weight': [0.2,0.3,0.5,0.6, 0.7,0.9]\n","}\n","\n","grid_search_clf = grid_search_wrapper(refit_score='recall_score')\n","\n","gsf= grid_search_clf.best_estimator_\n","gsf.fit(xtrain[indx],ytrain)"],"execution_count":null,"outputs":[{"output_type":"stream","text":["Fitting 10 folds for each of 6 candidates, totalling 60 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.3min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.3min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 2.6min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 3.9min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.0min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 5.3min\n","[Parallel(n_jobs=-1)]: Done 8 tasks | elapsed: 5.3min\n","[Parallel(n_jobs=-1)]: Done 9 tasks | elapsed: 6.6min\n","[Parallel(n_jobs=-1)]: Done 10 tasks | elapsed: 6.6min\n","[Parallel(n_jobs=-1)]: Done 11 tasks | elapsed: 8.0min\n","[Parallel(n_jobs=-1)]: Done 12 tasks | elapsed: 8.0min\n","[Parallel(n_jobs=-1)]: Done 13 tasks | elapsed: 9.3min\n","[Parallel(n_jobs=-1)]: Done 14 tasks | elapsed: 9.3min\n","[Parallel(n_jobs=-1)]: Done 15 tasks | elapsed: 10.6min\n","[Parallel(n_jobs=-1)]: Done 16 tasks | elapsed: 10.7min\n","[Parallel(n_jobs=-1)]: Done 17 tasks | elapsed: 12.0min\n","[Parallel(n_jobs=-1)]: Done 18 tasks | elapsed: 12.0min\n","[Parallel(n_jobs=-1)]: Done 19 tasks | elapsed: 13.3min\n","[Parallel(n_jobs=-1)]: Done 20 tasks | elapsed: 13.3min\n","[Parallel(n_jobs=-1)]: Done 21 tasks | elapsed: 14.7min\n","[Parallel(n_jobs=-1)]: Done 22 tasks | elapsed: 14.7min\n","[Parallel(n_jobs=-1)]: Done 23 tasks | elapsed: 16.0min\n","[Parallel(n_jobs=-1)]: Done 24 tasks | elapsed: 16.1min\n","[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 17.5min\n","[Parallel(n_jobs=-1)]: Done 26 tasks | elapsed: 17.5min\n","[Parallel(n_jobs=-1)]: Done 27 tasks | elapsed: 18.8min\n","[Parallel(n_jobs=-1)]: Done 28 tasks | elapsed: 18.8min\n","[Parallel(n_jobs=-1)]: Done 29 tasks | elapsed: 20.2min\n","[Parallel(n_jobs=-1)]: Done 30 tasks | elapsed: 20.2min\n","[Parallel(n_jobs=-1)]: Done 31 tasks | elapsed: 21.5min\n","[Parallel(n_jobs=-1)]: Done 32 tasks | elapsed: 21.6min\n","[Parallel(n_jobs=-1)]: Done 33 tasks | elapsed: 22.9min\n","[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 22.9min\n","[Parallel(n_jobs=-1)]: Done 35 tasks | elapsed: 24.3min\n","[Parallel(n_jobs=-1)]: Done 36 tasks | elapsed: 24.3min\n","[Parallel(n_jobs=-1)]: Done 37 tasks | elapsed: 25.6min\n","[Parallel(n_jobs=-1)]: Done 38 tasks | elapsed: 25.7min\n","[Parallel(n_jobs=-1)]: Done 39 tasks | elapsed: 27.1min\n","[Parallel(n_jobs=-1)]: Done 40 tasks | elapsed: 27.1min\n","[Parallel(n_jobs=-1)]: Done 41 tasks | elapsed: 28.4min\n","[Parallel(n_jobs=-1)]: Done 42 tasks | elapsed: 28.5min\n","[Parallel(n_jobs=-1)]: Done 43 tasks | elapsed: 29.8min\n","[Parallel(n_jobs=-1)]: Done 44 tasks | elapsed: 29.9min\n","[Parallel(n_jobs=-1)]: Done 45 tasks | elapsed: 31.2min\n","[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 31.2min\n","[Parallel(n_jobs=-1)]: Done 47 tasks | elapsed: 32.5min\n","[Parallel(n_jobs=-1)]: Done 48 tasks | elapsed: 32.6min\n","[Parallel(n_jobs=-1)]: Done 49 tasks | elapsed: 33.9min\n","[Parallel(n_jobs=-1)]: Done 50 tasks | elapsed: 34.0min\n","[Parallel(n_jobs=-1)]: Done 51 tasks | elapsed: 35.3min\n","[Parallel(n_jobs=-1)]: Done 52 tasks | elapsed: 35.3min\n","[Parallel(n_jobs=-1)]: Done 53 tasks | elapsed: 36.6min\n","[Parallel(n_jobs=-1)]: Done 54 tasks | elapsed: 36.7min\n","[Parallel(n_jobs=-1)]: Done 55 tasks | elapsed: 38.1min\n","[Parallel(n_jobs=-1)]: Done 56 tasks | elapsed: 38.1min\n","[Parallel(n_jobs=-1)]: Done 57 tasks | elapsed: 39.5min\n","[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 40.9min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 40.9min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for recall_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'max_depth': 5, 'min_child_weight': 10, 'n_estimators': 500, 'scale_pos_weight': 0.9, 'subsample': 0.3}\n","\n","Confusion matrix of Random Forest optimized for recall_score on the test data:\n"," pred_neg pred_pos\n","neg 14716 1541\n","pos 1609 663\n"],"name":"stdout"},{"output_type":"execute_result","data":{"text/plain":["XGBClassifier(base_score=0.5, booster='gbtree',\n"," class_weight={0: 0.877, 1: 0.122}, colsample_bylevel=1,\n"," colsample_bynode=1, colsample_bytree=1, gamma=0,\n"," learning_rate=0.9, max_delta_step=0, max_depth=5,\n"," min_child_weight=10, missing=None, n_estimators=500, n_jobs=1,\n"," nthread=None, objective='binary:logistic', random_state=0,\n"," reg_alpha=0, reg_lambda=1, scale_pos_weight=0.9, seed=None,\n"," silent=None, subsample=0.3, verbosity=1)"]},"metadata":{"tags":[]},"execution_count":26}]},{"cell_type":"code","metadata":{"id":"hv7ysLIZkpwR","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605720932857,"user_tz":-330,"elapsed":2543185,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"d6f79117-774b-4f1e-fcf7-1e2ea69144ff"},"source":["from xgboost import XGBClassifier\n","clf = XGBClassifier()\n","\n","param_grid = {\n"," 'learning_rate': [ 0.9],\n"," 'class_weight': [{1: 0.122, 0: 0.877}], 'n_estimators': [500],\n"," 'max_depth': [5],\n"," 'min_child_weight': [10],\n"," 'subsample': [0.3],\n"," 'scale_pos_weight': [0.2,0.3,0.5,0.6, 0.7,0.9]\n","}\n","\n","grid_search_clf = grid_search_wrapper(refit_score='recall_score')\n","\n","gsf= grid_search_clf.best_estimator_\n","gsf.fit(xtrain[indx],ytrain)"],"execution_count":59,"outputs":[{"output_type":"stream","text":["Fitting 10 folds for each of 6 candidates, totalling 60 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.3min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.3min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 2.7min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 2.7min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.0min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.0min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 5.3min\n","[Parallel(n_jobs=-1)]: Done 8 tasks | elapsed: 5.3min\n","[Parallel(n_jobs=-1)]: Done 9 tasks | elapsed: 6.7min\n","[Parallel(n_jobs=-1)]: Done 10 tasks | elapsed: 6.7min\n","[Parallel(n_jobs=-1)]: Done 11 tasks | elapsed: 8.0min\n","[Parallel(n_jobs=-1)]: Done 12 tasks | elapsed: 8.0min\n","[Parallel(n_jobs=-1)]: Done 13 tasks | elapsed: 9.3min\n","[Parallel(n_jobs=-1)]: Done 14 tasks | elapsed: 9.3min\n","[Parallel(n_jobs=-1)]: Done 15 tasks | elapsed: 10.7min\n","[Parallel(n_jobs=-1)]: Done 16 tasks | elapsed: 10.7min\n","[Parallel(n_jobs=-1)]: Done 17 tasks | elapsed: 12.0min\n","[Parallel(n_jobs=-1)]: Done 18 tasks | elapsed: 12.0min\n","[Parallel(n_jobs=-1)]: Done 19 tasks | elapsed: 13.4min\n","[Parallel(n_jobs=-1)]: Done 20 tasks | elapsed: 13.4min\n","[Parallel(n_jobs=-1)]: Done 21 tasks | elapsed: 14.8min\n","[Parallel(n_jobs=-1)]: Done 22 tasks | elapsed: 14.8min\n","[Parallel(n_jobs=-1)]: Done 23 tasks | elapsed: 16.2min\n","[Parallel(n_jobs=-1)]: Done 24 tasks | elapsed: 16.2min\n","[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 17.5min\n","[Parallel(n_jobs=-1)]: Done 26 tasks | elapsed: 17.5min\n","[Parallel(n_jobs=-1)]: Done 27 tasks | elapsed: 18.9min\n","[Parallel(n_jobs=-1)]: Done 28 tasks | elapsed: 18.9min\n","[Parallel(n_jobs=-1)]: Done 29 tasks | elapsed: 20.2min\n","[Parallel(n_jobs=-1)]: Done 30 tasks | elapsed: 20.2min\n","[Parallel(n_jobs=-1)]: Done 31 tasks | elapsed: 21.6min\n","[Parallel(n_jobs=-1)]: Done 32 tasks | elapsed: 21.6min\n","[Parallel(n_jobs=-1)]: Done 33 tasks | elapsed: 23.0min\n","[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 23.0min\n","[Parallel(n_jobs=-1)]: Done 35 tasks | elapsed: 24.4min\n","[Parallel(n_jobs=-1)]: Done 36 tasks | elapsed: 24.4min\n","[Parallel(n_jobs=-1)]: Done 37 tasks | elapsed: 25.8min\n","[Parallel(n_jobs=-1)]: Done 38 tasks | elapsed: 25.8min\n","[Parallel(n_jobs=-1)]: Done 39 tasks | elapsed: 27.1min\n","[Parallel(n_jobs=-1)]: Done 40 tasks | elapsed: 27.1min\n","[Parallel(n_jobs=-1)]: Done 41 tasks | elapsed: 28.5min\n","[Parallel(n_jobs=-1)]: Done 42 tasks | elapsed: 28.5min\n","[Parallel(n_jobs=-1)]: Done 43 tasks | elapsed: 29.8min\n","[Parallel(n_jobs=-1)]: Done 44 tasks | elapsed: 29.9min\n","[Parallel(n_jobs=-1)]: Done 45 tasks | elapsed: 31.2min\n","[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 31.3min\n","[Parallel(n_jobs=-1)]: Done 47 tasks | elapsed: 32.6min\n","[Parallel(n_jobs=-1)]: Done 48 tasks | elapsed: 32.7min\n","[Parallel(n_jobs=-1)]: Done 49 tasks | elapsed: 34.0min\n","[Parallel(n_jobs=-1)]: Done 50 tasks | elapsed: 34.1min\n","[Parallel(n_jobs=-1)]: Done 51 tasks | elapsed: 35.4min\n","[Parallel(n_jobs=-1)]: Done 52 tasks | elapsed: 35.5min\n","[Parallel(n_jobs=-1)]: Done 53 tasks | elapsed: 36.8min\n","[Parallel(n_jobs=-1)]: Done 54 tasks | elapsed: 36.8min\n","[Parallel(n_jobs=-1)]: Done 55 tasks | elapsed: 38.2min\n","[Parallel(n_jobs=-1)]: Done 56 tasks | elapsed: 38.2min\n","[Parallel(n_jobs=-1)]: Done 57 tasks | elapsed: 39.5min\n","[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 40.9min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 40.9min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for recall_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'max_depth': 5, 'min_child_weight': 10, 'n_estimators': 500, 'scale_pos_weight': 0.9, 'subsample': 0.3}\n","\n","Confusion matrix of Random Forest optimized for recall_score on the test data:\n"," pred_neg pred_pos\n","neg 14661 1596\n","pos 1655 617\n"],"name":"stdout"},{"output_type":"execute_result","data":{"text/plain":["XGBClassifier(base_score=0.5, booster='gbtree',\n"," class_weight={0: 0.877, 1: 0.122}, colsample_bylevel=1,\n"," colsample_bynode=1, colsample_bytree=1, gamma=0,\n"," learning_rate=0.9, max_delta_step=0, max_depth=5,\n"," min_child_weight=10, missing=None, n_estimators=500, n_jobs=1,\n"," nthread=None, objective='binary:logistic', random_state=0,\n"," reg_alpha=0, reg_lambda=1, scale_pos_weight=0.9, seed=None,\n"," silent=None, subsample=0.3, verbosity=1)"]},"metadata":{"tags":[]},"execution_count":59}]},{"cell_type":"code","metadata":{"id":"EJvAkPLtrj07","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605723438223,"user_tz":-330,"elapsed":2505328,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"80563a8b-4371-4a6a-c69d-2ba38357cc21"},"source":["from xgboost import XGBClassifier\n","clf = XGBClassifier()\n","\n","param_grid = {\n"," 'learning_rate': [ 0.9],\n"," 'class_weight': [{1: 0.122, 0: 0.877}], 'n_estimators': [500],\n"," 'max_depth': [5],\n"," 'min_child_weight': [10],\n"," 'subsample': [0.3],\n"," 'scale_pos_weight': [0.8,0.9,1,9]\n","}\n","\n","grid_search_clf = grid_search_wrapper(refit_score='roc_auc_score')\n","\n","gsf= grid_search_clf.best_estimator_\n","\n"],"execution_count":60,"outputs":[{"output_type":"stream","text":["Fitting 10 folds for each of 6 candidates, totalling 60 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n","[Parallel(n_jobs=-1)]: Done 1 tasks | elapsed: 1.4min\n","[Parallel(n_jobs=-1)]: Done 2 tasks | elapsed: 1.4min\n","[Parallel(n_jobs=-1)]: Done 3 tasks | elapsed: 2.7min\n","[Parallel(n_jobs=-1)]: Done 4 tasks | elapsed: 2.7min\n","[Parallel(n_jobs=-1)]: Done 5 tasks | elapsed: 4.0min\n","[Parallel(n_jobs=-1)]: Done 6 tasks | elapsed: 4.0min\n","[Parallel(n_jobs=-1)]: Done 7 tasks | elapsed: 5.3min\n","[Parallel(n_jobs=-1)]: Done 8 tasks | elapsed: 5.3min\n","[Parallel(n_jobs=-1)]: Done 9 tasks | elapsed: 6.6min\n","[Parallel(n_jobs=-1)]: Done 10 tasks | elapsed: 6.6min\n","[Parallel(n_jobs=-1)]: Done 11 tasks | elapsed: 7.9min\n","[Parallel(n_jobs=-1)]: Done 12 tasks | elapsed: 8.0min\n","[Parallel(n_jobs=-1)]: Done 13 tasks | elapsed: 9.3min\n","[Parallel(n_jobs=-1)]: Done 14 tasks | elapsed: 9.3min\n","[Parallel(n_jobs=-1)]: Done 15 tasks | elapsed: 10.7min\n","[Parallel(n_jobs=-1)]: Done 16 tasks | elapsed: 10.7min\n","[Parallel(n_jobs=-1)]: Done 17 tasks | elapsed: 12.0min\n","[Parallel(n_jobs=-1)]: Done 18 tasks | elapsed: 12.0min\n","[Parallel(n_jobs=-1)]: Done 19 tasks | elapsed: 13.3min\n","[Parallel(n_jobs=-1)]: Done 20 tasks | elapsed: 13.4min\n","[Parallel(n_jobs=-1)]: Done 21 tasks | elapsed: 14.7min\n","[Parallel(n_jobs=-1)]: Done 22 tasks | elapsed: 14.7min\n","[Parallel(n_jobs=-1)]: Done 23 tasks | elapsed: 16.0min\n","[Parallel(n_jobs=-1)]: Done 24 tasks | elapsed: 16.1min\n","[Parallel(n_jobs=-1)]: Done 25 tasks | elapsed: 17.4min\n","[Parallel(n_jobs=-1)]: Done 26 tasks | elapsed: 17.4min\n","[Parallel(n_jobs=-1)]: Done 27 tasks | elapsed: 18.7min\n","[Parallel(n_jobs=-1)]: Done 28 tasks | elapsed: 18.8min\n","[Parallel(n_jobs=-1)]: Done 29 tasks | elapsed: 20.1min\n","[Parallel(n_jobs=-1)]: Done 30 tasks | elapsed: 20.1min\n","[Parallel(n_jobs=-1)]: Done 31 tasks | elapsed: 21.5min\n","[Parallel(n_jobs=-1)]: Done 32 tasks | elapsed: 21.5min\n","[Parallel(n_jobs=-1)]: Done 33 tasks | elapsed: 22.9min\n","[Parallel(n_jobs=-1)]: Done 34 tasks | elapsed: 22.9min\n","[Parallel(n_jobs=-1)]: Done 35 tasks | elapsed: 24.2min\n","[Parallel(n_jobs=-1)]: Done 36 tasks | elapsed: 24.2min\n","[Parallel(n_jobs=-1)]: Done 37 tasks | elapsed: 25.6min\n","[Parallel(n_jobs=-1)]: Done 38 tasks | elapsed: 25.6min\n","[Parallel(n_jobs=-1)]: Done 39 tasks | elapsed: 26.9min\n","[Parallel(n_jobs=-1)]: Done 40 tasks | elapsed: 27.0min\n","[Parallel(n_jobs=-1)]: Done 41 tasks | elapsed: 28.3min\n","[Parallel(n_jobs=-1)]: Done 42 tasks | elapsed: 28.3min\n","[Parallel(n_jobs=-1)]: Done 43 tasks | elapsed: 29.6min\n","[Parallel(n_jobs=-1)]: Done 44 tasks | elapsed: 29.7min\n","[Parallel(n_jobs=-1)]: Done 45 tasks | elapsed: 31.1min\n","[Parallel(n_jobs=-1)]: Done 46 tasks | elapsed: 31.1min\n","[Parallel(n_jobs=-1)]: Done 47 tasks | elapsed: 32.4min\n","[Parallel(n_jobs=-1)]: Done 48 tasks | elapsed: 32.5min\n","[Parallel(n_jobs=-1)]: Done 49 tasks | elapsed: 33.8min\n","[Parallel(n_jobs=-1)]: Done 50 tasks | elapsed: 33.8min\n","[Parallel(n_jobs=-1)]: Done 51 tasks | elapsed: 35.1min\n","[Parallel(n_jobs=-1)]: Done 52 tasks | elapsed: 35.2min\n","[Parallel(n_jobs=-1)]: Done 53 tasks | elapsed: 36.5min\n","[Parallel(n_jobs=-1)]: Done 54 tasks | elapsed: 36.5min\n","[Parallel(n_jobs=-1)]: Done 55 tasks | elapsed: 37.9min\n","[Parallel(n_jobs=-1)]: Done 56 tasks | elapsed: 37.9min\n","[Parallel(n_jobs=-1)]: Done 57 tasks | elapsed: 39.2min\n","[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 40.6min remaining: 0.0s\n","[Parallel(n_jobs=-1)]: Done 60 out of 60 | elapsed: 40.6min finished\n"],"name":"stderr"},{"output_type":"stream","text":["Best params for roc_auc_score\n","{'class_weight': {1: 0.122, 0: 0.877}, 'learning_rate': 0.9, 'max_depth': 5, 'min_child_weight': 10, 'n_estimators': 500, 'scale_pos_weight': 0.9, 'subsample': 0.3}\n","\n","Confusion matrix of Random Forest optimized for roc_auc_score on the test data:\n"," pred_neg pred_pos\n","neg 14661 1596\n","pos 1655 617\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"j5w1_DJPAhmL","executionInfo":{"status":"ok","timestamp":1605792736442,"user_tz":-330,"elapsed":873,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}}},"source":["\n","gsf=XGBClassifier(base_score=0.5, booster='gbtree',\n"," class_weight={0: 0.877, 1: 0.122}, colsample_bylevel=1,\n"," colsample_bynode=1, colsample_bytree=1, gamma=0,\n"," learning_rate=0.9, max_delta_step=0, max_depth=5,\n"," min_child_weight=10, missing=None, n_estimators=500, n_jobs=1,\n"," nthread=None, objective='binary:logistic', random_state=0,\n"," reg_alpha=0, reg_lambda=1, scale_pos_weight=0.9, seed=None,\n"," silent=None, subsample=0.3, verbosity=1)"],"execution_count":42,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"wNEMuM_joOHW","executionInfo":{"status":"ok","timestamp":1605724341503,"user_tz":-330,"elapsed":2327,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"11c79f78-7e12-4b91-d859-4b32167c154a"},"source":["gsf.fit(xtrain[indx],ytrain)\n","preds = gsf.predict(xtest[indx])\n","roc_auc_score(ytest, preds)"],"execution_count":61,"outputs":[{"output_type":"execute_result","data":{"text/plain":["XGBClassifier(base_score=0.5, booster='gbtree',\n"," class_weight={0: 0.877, 1: 0.122}, colsample_bylevel=1,\n"," colsample_bynode=1, colsample_bytree=1, gamma=0,\n"," learning_rate=0.9, max_delta_step=0, max_depth=5,\n"," min_child_weight=10, missing=None, n_estimators=500, n_jobs=1,\n"," nthread=None, objective='binary:logistic', random_state=0,\n"," reg_alpha=0, reg_lambda=1, scale_pos_weight=0.9, seed=None,\n"," silent=None, subsample=0.3, verbosity=1)"]},"metadata":{"tags":[]},"execution_count":61}]},{"cell_type":"code","metadata":{"id":"lOEniusYuToh","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605793788954,"user_tz":-330,"elapsed":245146,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"e6b29b58-59c5-46b3-b147-188cd9096fc1"},"source":["from xgboost import XGBClassifier\n","xgb_model= XGBClassifier()\n","param_tuning = {\n"," 'learning_rate': [0.25],\n"," \"class_weight\":[{0:0.877,1:0.123}],\n"," 'max_depth': [3],\n"," 'min_child_weight': [5],\n"," 'subsample': [0.7],\n"," 'colsample_bytree': [0.05,0.1,0.2,0.5, 0.7,0.9],\n"," 'n_estimators' : [500] \n","}\n","\n","xgbsearch3 = GridSearchCV(estimator = xgb_model,\n"," param_grid = param_tuning, \n"," cv = 5,scoring ='roc_auc',\n"," n_jobs = 20,\n"," verbose = 30)\n","\n","xgbsearch3.fit(xtrain[indx],ytrain)\n","print(xgbsearch3.best_params_)\n","report(xgbsearch3.cv_results_,5)"],"execution_count":53,"outputs":[{"output_type":"stream","text":["Fitting 5 folds for each of 6 candidates, totalling 30 fits\n"],"name":"stdout"},{"output_type":"stream","text":["[Parallel(n_jobs=20)]: Using backend LokyBackend with 20 concurrent workers.\n","[Parallel(n_jobs=20)]: Done 1 tasks | elapsed: 27.2s\n","[Parallel(n_jobs=20)]: Done 3 out of 30 | elapsed: 27.4s remaining: 4.1min\n","[Parallel(n_jobs=20)]: Done 5 out of 30 | elapsed: 28.4s remaining: 2.4min\n","[Parallel(n_jobs=20)]: Done 7 out of 30 | elapsed: 1.9min remaining: 6.3min\n","[Parallel(n_jobs=20)]: Done 9 out of 30 | elapsed: 1.9min remaining: 4.5min\n","[Parallel(n_jobs=20)]: Done 11 out of 30 | elapsed: 2.2min remaining: 3.8min\n","[Parallel(n_jobs=20)]: Done 13 out of 30 | elapsed: 2.2min remaining: 2.9min\n","[Parallel(n_jobs=20)]: Done 15 out of 30 | elapsed: 2.2min remaining: 2.2min\n","[Parallel(n_jobs=20)]: Done 17 out of 30 | elapsed: 2.8min remaining: 2.2min\n","[Parallel(n_jobs=20)]: Done 19 out of 30 | elapsed: 2.8min remaining: 1.6min\n","[Parallel(n_jobs=20)]: Done 21 out of 30 | elapsed: 3.1min remaining: 1.3min\n","[Parallel(n_jobs=20)]: Done 23 out of 30 | elapsed: 3.7min remaining: 1.1min\n","[Parallel(n_jobs=20)]: Done 25 out of 30 | elapsed: 3.7min remaining: 44.7s\n","[Parallel(n_jobs=20)]: Done 27 out of 30 | elapsed: 3.8min remaining: 25.4s\n","[Parallel(n_jobs=20)]: Done 30 out of 30 | elapsed: 3.8min finished\n"],"name":"stderr"},{"output_type":"stream","text":["{'class_weight': {0: 0.877, 1: 0.123}, 'colsample_bytree': 0.5, 'learning_rate': 0.25, 'max_depth': 3, 'min_child_weight': 5, 'n_estimators': 500, 'subsample': 0.7}\n","Model with rank: 1\n","Mean validation score: 0.727 (std: 0.00236)\n","Parameters: {'class_weight': {0: 0.877, 1: 0.123}, 'colsample_bytree': 0.5, 'learning_rate': 0.25, 'max_depth': 3, 'min_child_weight': 5, 'n_estimators': 500, 'subsample': 0.7}\n","\n","Model with rank: 2\n","Mean validation score: 0.726 (std: 0.00308)\n","Parameters: {'class_weight': {0: 0.877, 1: 0.123}, 'colsample_bytree': 0.7, 'learning_rate': 0.25, 'max_depth': 3, 'min_child_weight': 5, 'n_estimators': 500, 'subsample': 0.7}\n","\n","Model with rank: 3\n","Mean validation score: 0.725 (std: 0.00295)\n","Parameters: {'class_weight': {0: 0.877, 1: 0.123}, 'colsample_bytree': 0.9, 'learning_rate': 0.25, 'max_depth': 3, 'min_child_weight': 5, 'n_estimators': 500, 'subsample': 0.7}\n","\n","Model with rank: 4\n","Mean validation score: 0.724 (std: 0.00399)\n","Parameters: {'class_weight': {0: 0.877, 1: 0.123}, 'colsample_bytree': 0.2, 'learning_rate': 0.25, 'max_depth': 3, 'min_child_weight': 5, 'n_estimators': 500, 'subsample': 0.7}\n","\n","Model with rank: 5\n","Mean validation score: 0.715 (std: 0.00595)\n","Parameters: {'class_weight': {0: 0.877, 1: 0.123}, 'colsample_bytree': 0.05, 'learning_rate': 0.25, 'max_depth': 3, 'min_child_weight': 5, 'n_estimators': 500, 'subsample': 0.7}\n","\n","Model with rank: 5\n","Mean validation score: 0.715 (std: 0.00595)\n","Parameters: {'class_weight': {0: 0.877, 1: 0.123}, 'colsample_bytree': 0.1, 'learning_rate': 0.25, 'max_depth': 3, 'min_child_weight': 5, 'n_estimators': 500, 'subsample': 0.7}\n","\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"3jt68j_r1Hg6","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1605797334880,"user_tz":-330,"elapsed":13030,"user":{"displayName":"Mansi Gupta","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14Gg-eSqQt6zvClgSY0_QT_GIvO_LGNz3Cau1wv1S7w=s64","userId":"09741357658171476289"}},"outputId":"b67aae6e-aa5e-4662-f2f5-dd8d9e73a00c"},"source":["xgbfinal = xgbsearch3.best_estimator_\n","xgbfinal.fit(xtrain[indx],ytrain)\n","preds=xgbfinal.predict(xtest[indx])\n","print(confusion_matrix(ytest,preds))"],"execution_count":55,"outputs":[{"output_type":"stream","text":["[[16002 255]\n"," [ 1773 499]]\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"-PYdQD4K3yVl"},"source":["\n"],"execution_count":null,"outputs":[]}]}