├── model.sav ├── churm analysis.pbix ├── LICENSE ├── first_telc.csv ├── Pages └── prediction.py ├── Customer Churn Knowledge.py └── Churn Analysis - Model Building.ipynb /model.sav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rohanmistry231/Customer-Churn-Analysis-and-Classification/HEAD/model.sav -------------------------------------------------------------------------------- /churm analysis.pbix: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rohanmistry231/Customer-Churn-Analysis-and-Classification/HEAD/churm analysis.pbix -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2025 rohanmistry231 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /first_telc.csv: -------------------------------------------------------------------------------- 1 | ,gender,SeniorCitizen,Partner,Dependents,tenure,PhoneService,MultipleLines,InternetService,OnlineSecurity,OnlineBackup,DeviceProtection,TechSupport,StreamingTV,StreamingMovies,Contract,PaperlessBilling,PaymentMethod,MonthlyCharges,TotalCharges 2 | 0,Female,0,Yes,No,1,No,No phone service,DSL,No,Yes,No,No,No,No,Month-to-month,Yes,Electronic check,29.85,29.85 3 | 1,Male,0,No,No,34,Yes,No,DSL,Yes,No,Yes,No,No,No,One year,No,Mailed check,56.95,1889.5 4 | 3,Male,0,No,No,45,No,No phone service,DSL,Yes,No,Yes,Yes,No,No,One year,No,Bank transfer (automatic),42.3,1840.75 5 | 6,Male,0,No,Yes,22,Yes,Yes,Fiber optic,No,Yes,No,No,Yes,No,Month-to-month,Yes,Credit card (automatic),89.1,1949.4 6 | 11,Male,0,No,No,16,Yes,No,No,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,Two year,No,Credit card (automatic),18.95,326.8 7 | 5,Female,0,No,No,8,Yes,Yes,Fiber optic,No,No,Yes,No,Yes,Yes,Month-to-month,Yes,Electronic check,99.65,820.5 8 | 4,Female,0,No,No,2,Yes,No,Fiber optic,No,No,No,No,No,No,Month-to-month,Yes,Electronic check,70.7,151.65 9 | 2,Male,0,No,No,2,Yes,No,DSL,Yes,Yes,No,No,No,No,Month-to-month,Yes,Mailed check,53.85,108.15 10 | 7,Female,0,No,No,10,No,No phone service,DSL,Yes,No,No,No,No,No,Month-to-month,No,Mailed check,29.75,301.9 11 | 8,Female,0,Yes,No,28,Yes,Yes,Fiber optic,No,No,Yes,Yes,Yes,Yes,Month-to-month,Yes,Electronic check,104.8,3046.05 12 | 9,Male,0,No,Yes,62,Yes,No,DSL,Yes,Yes,No,No,No,No,One year,No,Bank transfer (automatic),56.15,3487.95 13 | 10,Male,0,Yes,Yes,13,Yes,No,DSL,Yes,No,No,No,No,No,Month-to-month,Yes,Mailed check,49.95,587.45 14 | 12,Male,0,Yes,No,58,Yes,Yes,Fiber optic,No,No,Yes,No,Yes,Yes,One year,No,Credit card (automatic),100.35,5681.1 15 | 13,Male,0,No,No,49,Yes,Yes,Fiber optic,No,Yes,Yes,No,Yes,Yes,Month-to-month,Yes,Bank transfer (automatic),103.7,5036.3 16 | 14,Male,0,No,No,25,Yes,No,Fiber optic,Yes,No,Yes,Yes,Yes,Yes,Month-to-month,Yes,Electronic check,105.5,2686.05 17 | 15,Female,0,Yes,Yes,69,Yes,Yes,Fiber optic,Yes,Yes,Yes,Yes,Yes,Yes,Two year,No,Credit card (automatic),113.25,7895.15 18 | 16,Female,0,No,No,52,Yes,No,No,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,One year,No,Mailed check,20.65,1022.95 19 | 17,Male,0,No,Yes,71,Yes,Yes,Fiber optic,Yes,No,Yes,No,Yes,Yes,Two year,No,Bank transfer (automatic),106.7,7382.25 20 | 19,Female,0,No,No,21,Yes,No,Fiber optic,No,Yes,Yes,No,No,Yes,Month-to-month,Yes,Electronic check,90.05,1862.9 21 | 21,Male,0,Yes,No,12,Yes,No,No,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,One year,No,Bank transfer (automatic),19.8,202.25 22 | 25,Female,0,No,No,30,Yes,No,DSL,Yes,Yes,No,No,No,No,Month-to-month,Yes,Bank transfer (automatic),55.3,1530.6 23 | 26,Male,0,Yes,Yes,47,Yes,Yes,Fiber optic,No,Yes,No,No,Yes,Yes,Month-to-month,Yes,Electronic check,99.35,4749.15 24 | 28,Male,0,Yes,No,72,Yes,Yes,DSL,Yes,Yes,Yes,Yes,Yes,Yes,Two year,Yes,Credit card (automatic),90.25,6369.45 25 | 29,Female,0,No,Yes,17,Yes,No,DSL,No,No,No,No,Yes,Yes,Month-to-month,Yes,Mailed check,64.7,1093.1 26 | 32,Female,0,Yes,Yes,27,Yes,No,DSL,Yes,Yes,Yes,Yes,No,No,One year,No,Mailed check,66.15,1874.45 27 | 36,Male,0,No,No,5,Yes,No,Fiber optic,No,No,No,No,No,No,Month-to-month,Yes,Electronic check,69.7,316.9 28 | 37,Female,0,No,No,46,Yes,No,Fiber optic,No,No,Yes,No,No,No,Month-to-month,Yes,Credit card (automatic),74.8,3548.3 29 | 39,Female,0,No,No,11,Yes,Yes,Fiber optic,No,No,Yes,No,Yes,Yes,Month-to-month,Yes,Bank transfer (automatic),97.85,1105.4 30 | 41,Female,0,Yes,Yes,70,Yes,Yes,DSL,Yes,Yes,No,No,Yes,No,Two year,Yes,Credit card (automatic),69.2,4872.35 31 | 43,Female,0,No,No,63,Yes,Yes,DSL,Yes,Yes,Yes,Yes,Yes,No,Two year,Yes,Credit card (automatic),79.85,4861.45 32 | 50,Female,1,No,No,43,Yes,Yes,Fiber optic,No,Yes,No,No,Yes,No,Month-to-month,Yes,Electronic check,90.25,3838.75 33 | 51,Female,0,No,No,15,Yes,No,Fiber optic,Yes,Yes,No,No,Yes,Yes,Month-to-month,Yes,Credit card (automatic),99.1,1426.4 34 | 54,Female,1,Yes,Yes,60,Yes,No,DSL,Yes,Yes,Yes,Yes,No,Yes,One year,Yes,Credit card (automatic),74.85,4456.35 35 | 55,Male,1,No,No,18,Yes,Yes,Fiber optic,No,No,No,No,Yes,Yes,Month-to-month,Yes,Electronic check,95.45,1752.55 36 | 57,Male,1,Yes,Yes,66,Yes,Yes,Fiber optic,No,Yes,Yes,Yes,Yes,Yes,One year,Yes,Electronic check,108.45,7076.35 37 | 64,Female,0,No,No,9,Yes,Yes,Fiber optic,No,No,No,No,Yes,Yes,Month-to-month,No,Electronic check,94.4,857.25 38 | 65,Female,0,No,No,3,Yes,No,DSL,No,Yes,No,Yes,Yes,Yes,Month-to-month,Yes,Electronic check,75.3,244.1 39 | 67,Female,0,No,No,31,Yes,No,DSL,No,Yes,Yes,Yes,Yes,Yes,Two year,No,Mailed check,79.2,2497.2 40 | 68,Female,0,Yes,Yes,50,Yes,No,No,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,Two year,No,Bank transfer (automatic),20.15,930.9 41 | 72,Male,1,Yes,Yes,64,Yes,Yes,Fiber optic,Yes,No,Yes,Yes,Yes,Yes,Two year,Yes,Bank transfer (automatic),111.6,7099 42 | 75,Female,1,No,No,56,Yes,Yes,Fiber optic,Yes,Yes,Yes,No,Yes,Yes,One year,No,Electronic check,110.5,6139.5 43 | 82,Female,0,Yes,No,7,Yes,No,Fiber optic,No,No,Yes,No,No,No,Month-to-month,Yes,Bank transfer (automatic),75.15,496.9 44 | 83,Female,0,No,No,42,Yes,No,Fiber optic,No,Yes,Yes,Yes,Yes,Yes,Month-to-month,Yes,Bank transfer (automatic),103.8,4327.5 45 | 86,Female,0,Yes,No,35,Yes,No,DSL,Yes,No,No,No,Yes,No,One year,Yes,Bank transfer (automatic),62.15,2215.45 46 | 87,Female,0,Yes,Yes,48,Yes,No,No,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,Two year,No,Bank transfer (automatic),20.65,1057 47 | 89,Male,0,Yes,No,29,No,No phone service,DSL,No,No,No,No,Yes,No,Month-to-month,No,Mailed check,33.75,1009.25 48 | 93,Female,0,No,No,65,Yes,Yes,Fiber optic,Yes,Yes,Yes,No,Yes,Yes,Month-to-month,Yes,Credit card (automatic),111.05,7107 49 | 102,Male,0,No,No,38,Yes,Yes,Fiber optic,No,No,Yes,Yes,Yes,No,One year,No,Bank transfer (automatic),95.0,3605.6 50 | 104,Male,0,Yes,No,68,Yes,Yes,Fiber optic,No,Yes,Yes,Yes,Yes,Yes,Two year,Yes,Bank transfer (automatic),110.0,7611.85 51 | 107,Female,0,No,No,32,No,No phone service,DSL,Yes,No,No,No,No,No,One year,No,Mailed check,30.15,927.65 52 | 110,Male,0,Yes,No,55,Yes,Yes,Fiber optic,Yes,Yes,No,No,Yes,No,Month-to-month,Yes,Electronic check,96.75,5238.9 53 | 113,Female,1,Yes,No,37,Yes,Yes,Fiber optic,No,No,No,No,No,No,Month-to-month,Yes,Electronic check,76.5,2868.15 54 | 116,Female,0,No,No,36,No,No phone service,DSL,Yes,No,No,No,No,No,Two year,No,Bank transfer (automatic),31.05,1126.35 55 | 118,Female,0,No,No,41,Yes,No,No,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,Two year,No,Mailed check,20.65,835.15 56 | 121,Female,0,No,No,6,Yes,No,No,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,Month-to-month,No,Mailed check,20.7,112.75 57 | 124,Female,0,Yes,Yes,4,Yes,No,No,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,Month-to-month,No,Mailed check,20.85,62.9 58 | 125,Male,0,No,No,33,Yes,No,Fiber optic,Yes,No,No,Yes,Yes,No,Two year,Yes,Electronic check,88.95,3027.65 59 | 132,Male,0,No,No,67,Yes,No,DSL,No,No,No,Yes,No,No,Two year,No,Bank transfer (automatic),50.55,3260.1 60 | 136,Female,0,No,No,23,Yes,No,Fiber optic,Yes,No,No,No,No,No,Month-to-month,Yes,Bank transfer (automatic),75.0,1778.5 61 | 138,Male,0,No,Yes,57,Yes,No,No,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,Two year,Yes,Mailed check,19.6,1170.55 62 | 142,Female,0,Yes,No,61,Yes,Yes,Fiber optic,No,Yes,No,No,Yes,Yes,Two year,Yes,Bank transfer (automatic),101.05,5971.25 63 | 155,Female,0,Yes,Yes,14,Yes,No,Fiber optic,No,No,No,No,No,Yes,Month-to-month,Yes,Bank transfer (automatic),80.9,1152.8 64 | 161,Female,0,Yes,No,20,Yes,Yes,Fiber optic,Yes,No,No,No,No,No,Month-to-month,No,Electronic check,82.4,1592.35 65 | 163,Male,0,No,No,53,Yes,Yes,DSL,No,Yes,Yes,Yes,No,Yes,Two year,Yes,Bank transfer (automatic),73.9,3958.25 66 | 189,Female,0,Yes,No,40,Yes,Yes,DSL,No,Yes,No,No,No,No,Month-to-month,No,Credit card (automatic),56.6,2379.1 67 | 194,Male,0,Yes,Yes,59,Yes,No,No,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,Two year,No,Credit card (automatic),19.3,1192.7 68 | 196,Male,0,Yes,Yes,24,Yes,Yes,No,No internet service,No internet service,No internet service,No internet service,No internet service,No internet service,Two year,Yes,Bank transfer (automatic),24.1,587.4 69 | 204,Male,0,No,No,44,Yes,No,Fiber optic,No,No,No,No,No,No,Month-to-month,No,Credit card (automatic),68.85,2958.95 70 | 208,Female,0,No,No,19,Yes,No,Fiber optic,Yes,No,Yes,Yes,Yes,Yes,Month-to-month,Yes,Electronic check,106.6,1934.45 71 | 230,Male,0,No,No,54,Yes,Yes,Fiber optic,Yes,Yes,No,Yes,Yes,Yes,Two year,Yes,Credit card (automatic),108.0,5760.65 72 | 250,Female,0,Yes,No,51,Yes,No,Fiber optic,Yes,Yes,Yes,No,Yes,No,One year,Yes,Electronic check,93.5,4619.55 73 | 435,Female,0,No,No,26,No,No phone service,DSL,No,No,Yes,Yes,Yes,No,Month-to-month,Yes,Credit card (automatic),44.45,1183.8 74 | 488,Female,0,Yes,Yes,0,No,No phone service,DSL,Yes,No,Yes,Yes,Yes,No,Two year,Yes,Bank transfer (automatic),52.55, 75 | 546,Male,0,Yes,Yes,39,Yes,No,Fiber optic,No,Yes,No,No,Yes,No,Month-to-month,Yes,Mailed check,86.3,3266 76 | 20,Male,1,No,No,1,No,No phone service,DSL,No,No,Yes,No,No,Yes,Month-to-month,Yes,Electronic check,39.65,39.65 77 | -------------------------------------------------------------------------------- /Pages/prediction.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | import pickle 3 | import streamlit as st 4 | import pandas as pd 5 | from sklearn.model_selection import train_test_split 6 | 7 | churn_data = pd.read_csv( 8 | "C:\\Users\\Rohan S Mistry\\Downloads\\MLProject-ChurnPrediction-main\\MLProject-ChurnPrediction-main\\tel_churn.csv") 9 | x = churn_data.drop('Churn', axis=1) 10 | y = churn_data['Churn'] 11 | x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2) 12 | 13 | loaded_model = pickle.load(open( 14 | 'C:\\Users\\Rohan S Mistry\\Downloads\\MLProject-ChurnPrediction-main\\MLProject-ChurnPrediction-main\\model.sav', 'rb')) 15 | 16 | 17 | def chrun_prediction(input_data): 18 | 19 | input_data_as_numpy_array = np.asarray(input_data) 20 | input_data_reshaped = input_data_as_numpy_array.reshape(1, -1) 21 | prediction = loaded_model.predict(input_data_reshaped) 22 | print(prediction) 23 | 24 | if (prediction[0] == 0): 25 | return 'The person will not churn' 26 | else: 27 | return 'The person will churn' 28 | 29 | 30 | def main(): 31 | 32 | st.title(":green[How to Use Prediction System]") 33 | st.subheader( 34 | "Just Enter all parameters in Prediction Page and click on :blue[Churn Analysis Prediction.]") 35 | 36 | st.subheader("Enter Your Data") 37 | 38 | SeniorCitizen = st.text_input( 39 | 'SeniorCitizen ( If a person is SeniorCitizen Enter = 1 | else Enter = 0 )') 40 | MonthlyCharges = st.text_input( 41 | 'MonthlyCharges ( Enter your Monthy Charges rate )') 42 | TotalCharges = st.text_input( 43 | 'TotalCharges ( Enter your Total Charges rate )') 44 | gender_Female = st.text_input( 45 | 'gender_Female ( If a person is Female Enter = 1 | else Enter = 0 )') 46 | gender_Male = st.text_input( 47 | 'gender_Male ( If a person is Male Enter = 1 | else Enter = 0 )') 48 | Partner_No = st.text_input( 49 | 'Partner_No ( If There is No Partner Enter = 1 | else Enter = 0 )') 50 | Partner_Yes = st.text_input( 51 | 'Partner_Yes ( If There is Any Partner Enter = 1 | else Enter = 0 )') 52 | Dependents_No = st.text_input( 53 | 'Dependents_No ( If There is No Dependents Enter = 1 | else Enter = 0 )') 54 | Dependents_Yes = st.text_input( 55 | 'Dependents_Yes ( If There is Any Dependents Enter = 1 | else Enter = 0 )') 56 | PhoneService_No = st.text_input( 57 | 'PhoneService_No ( If There is No Phone Service Enter = 1 | else Enter = 0 )') 58 | PhoneService_Yes = st.text_input( 59 | 'PhoneService_Yes ( If There is Any Phone Service Enter = 1 | else Enter = 0 )') 60 | MultipleLines_No = st.text_input( 61 | 'MultipleLines_No ( If There is No Multiple Lines Enter = 1 | else Enter = 0 )') 62 | MultipleLines_No_phone_service = st.text_input( 63 | 'MultipleLines_No phone service ( If There is No Phone Service Multiple Lines Enter = 1 | else Enter = 0 )') 64 | MultipleLines_Yes = st.text_input( 65 | 'MultipleLines_Yes ( If There is Any Multiple Lines Enter = 1 | else Enter = 0 )') 66 | InternetService_DSL = st.text_input( 67 | 'InternetService_DSL ( If Internet Service is DSL Enter = 1 | else Enter = 0 )') 68 | InternetService_Fiber_optic = st.text_input( 69 | 'InternetService_Fiber optic ( If Internet Service is Fiber Optic Enter = 1 | else Enter = 0 )') 70 | InternetService_No = st.text_input( 71 | 'InternetService_No ( If There is No Internet Service Enter = 1 | else Enter = 0 )') 72 | OnlineSecurity_No = st.text_input( 73 | 'OnlineSecurity_No ( If There is No Online Security Enter = 1 | else Enter = 0 )') 74 | OnlineSecurity_No_internet_service = st.text_input( 75 | 'OnlineSecurity_No internet service ( If There is No Internet Service Online Security Enter = 1 | else Enter = 0 )') 76 | OnlineSecurity_Yes = st.text_input( 77 | 'OnlineSecurity_Yes ( If There is Any Online Security Enter = 1 | else Enter = 0 )') 78 | OnlineBackup_No = st.text_input( 79 | 'OnlineBackup_No ( If There is No Online Backup Enter = 1 | else Enter = 0 )') 80 | OnlineBackup_No_internet_service = st.text_input( 81 | 'OnlineBackup_No internet service ( If There is No Internet Service Online Backup Enter = 1 | else Enter = 0 )') 82 | OnlineBackup_Yes = st.text_input( 83 | 'OnlineBackup_Yes ( If There is Any Online Backup Enter = 1 | else Enter = 0 )') 84 | DeviceProtection_No = st.text_input( 85 | 'DeviceProtection_No ( If there is No Device Protection Enter = 1 | else Enter = 0 )') 86 | DeviceProtection_No_internet_service = st.text_input( 87 | 'DeviceProtection_No internet service ( If There is No Internet Service Device Protection Enter = 1 | else Enter = 0 )') 88 | DeviceProtection_Yes = st.text_input( 89 | 'DeviceProtection_Yes ( If There is Any Device Protection Enter = 1 | else Enter = 0 )') 90 | TechSupport_No = st.text_input( 91 | 'TechSupport_No ( If There is No Tech Support Enter = 1 | else Enter = 0 )') 92 | TechSupport_No_internet_service = st.text_input( 93 | 'TechSupport_No internet service ( If There is No Internet Service Tech Support Enter = 1 | else Enter = 0 )') 94 | TechSupport_Yes = st.text_input( 95 | 'TechSupport_Yes ( If There is Any Tech Support Enter = 1 | else Enter = 0 )') 96 | StreamingTV_No = st.text_input( 97 | 'StreamingTV_No ( If There is No SteamingTV Enter = 1 | else Enter = 0 )') 98 | StreamingTV_No_internet_service = st.text_input( 99 | 'StreamingTV_No internet service ( If There is No Internet Service StreamingTV Enter = 1 | else Enter = 0 )') 100 | StreamingTV_Yes = st.text_input( 101 | 'StreamingTV_Yes ( If There is Any StreamingTV Enter = 1 | else Enter = 0 )') 102 | StreamingMovies_No = st.text_input( 103 | 'StreamingMovies_No ( If There is No Streaming Movies Enter = 1 | else Enter = 0 )') 104 | StreamingMovies_No_internet_service = st.text_input( 105 | 'StreamingMovies_No internet service ( If There is No Internet Service Streaming Movies Enter = 1 | else Enter = 0 )') 106 | StreamingMovies_Yes = st.text_input( 107 | 'StreamingMovies_Yes ( If There is Any Streaming Movies Enter = 1 | else Enter = 0 )') 108 | Contract_Month_to_month = st.text_input( 109 | 'Contract_Month-to-month ( If There is Any Month-To_Month Contract Enter = 1 | else Enter = 0 )') 110 | Contract_One_year = st.text_input( 111 | 'Contract_One year ( If There is Any One Year Contract Enter = 1 | else Enter = 0 )') 112 | Contract_Two_year = st.text_input( 113 | 'Contract_Two year ( If There is Any Two Year Contract Enter = 1 | else Enter = 0 )') 114 | PaperlessBilling_No = st.text_input( 115 | 'PaperlessBilling_No ( If There is No Paperless Billing Enter = 1 | else Enter = 0 )') 116 | PaperlessBilling_Yes = st.text_input( 117 | 'PaperlessBilling_Yes ( If There is Any Paperless Billing Enter = 1 | else Enter = 0 )') 118 | PaymentMethod_Bank_transfer_automatic = st.text_input( 119 | 'PaymentMethod_Bank transfer (automatic) ( If a Person Use Any Automatic Bank_Transfer Payment Method Enter = 1 | else Enter = 0 )') 120 | PaymentMethod_Credit_card_automatic = st.text_input( 121 | 'PaymentMethod_Credit card (automatic) ( If a Person Use Any Automatic Credit_Card Payment Method Enter = 1 | else Enter = 0 )') 122 | PaymentMethod_Electronic_check = st.text_input( 123 | 'PaymentMethod_Electronic check ( If a Person Use Any Automatic Electronic_Check Payment Method Enter = 1 | else Enter = 0 )') 124 | PaymentMethod_Mailed_check = st.text_input( 125 | 'PaymentMethod_Mailed check ( If a Person Use Any Automatic Mailed_Check Payment Method Enter = 1 | else Enter = 0 )') 126 | tenure_group_1_12 = st.text_input( 127 | 'tenure_group_1 - 12 ( If a Person"s Tenure is Between 1 to 12 Enter = 1 | else Enter = 0 )') 128 | tenure_group_13_24 = st.text_input( 129 | 'tenure_group_13 - 24 ( If a Person"s Tenure is Between 13 to 24 Enter = 1 | else Enter = 0 )') 130 | tenure_group_25_36 = st.text_input( 131 | 'tenure_group_25 - 36 ( If a Person"s Tenure is Between 25 to 36 Enter = 1 | else Enter = 0 )') 132 | tenure_group_37_48 = st.text_input( 133 | 'tenure_group_37 - 48 ( If a Person"s Tenure is Between 37 to 48 Enter = 1 | else Enter = 0 )') 134 | tenure_group_49_60 = st.text_input( 135 | 'tenure_group_49 - 60 ( If a Person"s Tenure is Between 49 to 60 Enter = 1 | else Enter = 0 )') 136 | tenure_group_61_72 = st.text_input( 137 | 'tenure_group_61 - 72 ( If a Person"s Tenure is Between 61 to 72 Enter = 1 | else Enter = 0 )') 138 | 139 | predict = '' 140 | 141 | if st.button('Churn Analysis Prediction'): 142 | predict = chrun_prediction([SeniorCitizen, MonthlyCharges, TotalCharges, gender_Female, gender_Male, Partner_No, Partner_Yes, Dependents_No, Dependents_Yes, PhoneService_No, PhoneService_Yes, MultipleLines_No, MultipleLines_No_phone_service, MultipleLines_Yes, InternetService_DSL, InternetService_Fiber_optic, InternetService_No, OnlineSecurity_No, OnlineSecurity_No_internet_service, OnlineSecurity_Yes, OnlineBackup_No, OnlineBackup_No_internet_service, OnlineBackup_Yes, DeviceProtection_No, DeviceProtection_No_internet_service, DeviceProtection_Yes, TechSupport_No, 143 | TechSupport_No_internet_service, TechSupport_Yes, StreamingTV_No, StreamingTV_No_internet_service, StreamingTV_Yes, StreamingMovies_No, StreamingMovies_No_internet_service, StreamingMovies_Yes, Contract_Month_to_month, Contract_One_year, Contract_Two_year, PaperlessBilling_No, PaperlessBilling_Yes, PaymentMethod_Bank_transfer_automatic, PaymentMethod_Credit_card_automatic, PaymentMethod_Electronic_check, PaymentMethod_Mailed_check, tenure_group_1_12, tenure_group_13_24, tenure_group_25_36, tenure_group_37_48, tenure_group_49_60, tenure_group_61_72]) 144 | 145 | st.success(predict) 146 | 147 | 148 | if __name__ == '__main__': 149 | main() 150 | -------------------------------------------------------------------------------- /Customer Churn Knowledge.py: -------------------------------------------------------------------------------- 1 | import streamlit as st 2 | 3 | st.sidebar.success("Select above page.") 4 | 5 | st.title(":green[FAQs about Customer Churn]") 6 | st.subheader(":blue[1. What is Customer Churn ?]") 7 | st.write("Customer churn is the percentage of customers that stopped using your company's product or service during a certain time frame. You can calculate churn rate by dividing the number of customers you lost during that time period -- say a quarter -- by the number of customers you had at the beginning of that time period.") 8 | st.write("For example, if you start your quarter with 400 customers and end with 380, your churn rate is 5% because you lost 5% of your customers.") 9 | st.write("Obviously, your company should aim for a churn rate that is as close to 0% as possible. In order to do this, your company has to be on top of its churn rate at all times and treat it as a top priority.") 10 | st.write("In this example, I calculated the churn rate as the percentage of customers lost that quarter. However, you can calculate churn rate in whatever way is best for your company. Some examples are:") 11 | st.write("1. The number of customers lost") 12 | st.write("2. The value of recurring business lost") 13 | st.write("3. The percentage of recurring value lost") 14 | st.subheader(":blue[2. Why Is Customer Churn Rate Is Important ?]") 15 | st.write("You may be wondering why it's necessary to calculate churn rate. Naturally, you're going to lose some customers here and there, and 5% doesn't sound too bad, right?") 16 | st.write("Well, it's important because it costs more to acquire new customers than it does to retain existing customers. In fact, an increase in customer retention of just 5% can create at least a 25% increase in profit. This is because returning customers will likely spend 67% more on your company's products and services. As a result, your company can spend less on the operating costs of having to acquire new customers. You don't need to spend time and money on convincing an existing customer to select your company over competitors because they've already made that decision.") 17 | st.write("Again, it might seem like a 5% churn rate is solid and healthy. You can still make a vast revenue with that churn rate. However, consider the example below when thinking about the impact of your churn rate.") 18 | st.write("In this example, simply decreasing your churn rate by 10% could add an extra $100,000 in revenue to your company. Dropping from 3% to 2.7% doesn't seem like a lot, but it actually adds large benefits to your company.") 19 | st.subheader(":blue[3. How to Reduce Customer Churn ?]") 20 | st.subheader("1. Focus your attention on your best customers.") 21 | st.write("Rather than simply focusing on offering incentives to customers who are considering churning, it could be even more beneficial to pool your resources into your loyal, profitable customers.") 22 | st.subheader("2. Analyze churn as it occurs.") 23 | st.write("Use your churned customers as a means of understanding why customers are leaving. Analyze how and when churn occurs in a customer's lifetime with your company, and use that data to put into place preemptive measures.") 24 | st.subheader("3. Show your customers that you care.") 25 | st.write("Rather than simply focusing on offering incentives to customers who are considering churning, it could be even more beneficial to pool your resources into your loyal, profitable customers.") 26 | st.subheader(":blue[4. What is Customer Churn Rate ?]") 27 | st.write("Customer churn rate is the percentage of your customers or subscribers who cancel or don't renew their subscriptions during a given time period, such as a month or a year.") 28 | st.write("Churn rate is a critically important metric for companies whose customers pay on a recurring basis — like SaaS or other subscription-based companies. Regardless of your monthly revenue, if your typical customer doesn't stick around long enough for you to recoup your average customer acquisition cost (CAC), you're in trouble.") 29 | st.write("Using a CRM can help you determine your customer churn rate. The software you sell may also have a built-in subscriber count that shows you how many users you had at the beginning of a time period and how many users you had at the end.") 30 | st.subheader(":blue[5. Churn Rate Formula.]") 31 | st.write("The churn rate formula is: (Lost Customers ÷ Total Customers at the Start of Time Period) x 100. For example, if your business had 250 customers at the beginning of the month and lost 10 customers by the end, you would divide 10 by 250. The answer is 0.04. You then multiply 0.04 by 100, resulting in a 4% monthly churn rate.") 32 | st.subheader(":blue[6. How to Calculate Churn Rate ?]") 33 | st.write("To calculate churn rate, you need to have the number of customers you had at the beginning of a given time period, such as monthly or annually, and the number of customers you lost during that time period. Divide the number of lost customers by the total number of customers you had at the start of the time period. Then, multiply this number by 100 to get your churn rate as a percentage.") 34 | st.write("Remember, the steps to calculate churn rate are:") 35 | st.write("1. Determine a time period: monthly, annual, or quarterly.") 36 | st.write("2. Determine the number of customers you had at the beginning of the time period.") 37 | st.write("3. Determine the number of customers that churned by the end of the time period.") 38 | st.write("4. Divide the number of lost customers by the number of customers you had prior to the churn.") 39 | st.write("5. Multiply that number by 100.") 40 | st.write("As an example, let's say your software company had 500 customers at the beginning of last quarter.") 41 | st.write("However, you also lost 50 customers due to expired contracts and a few poor customer service interactions.") 42 | st.write("This would mean your quarter's customer churn rate would be the 50 churned customers divided by the 500 former customers, and 50 divided by 500 is 0.10.") 43 | st.write("Multiplied by 100, this gives you a customer churn rate of 10%.") 44 | st.write("Here's how it looks when you do the math out:") 45 | st.write("Customer Churn Rate = (Lost Customers ÷ Total Customers at the Start of Time Period) x 100") 46 | st.write("Customer Churn Rate = (50 ÷ 500) x 100") 47 | st.write("Customer Churn Rate = (0.10) x 100") 48 | st.write("Customer Churn Rate = 10%") 49 | st.write("Now that you've found out what your churn rate is, you're probably wondering what you should do next — especially if your churn rate is high. Take a look at the next section for some best practices that can help you decrease churn at your business.") 50 | st.subheader(":blue[7. Steps to Take After Calculating Churn Rate.]") 51 | st.write("Is your churn rate high? There are several strategies you could implement to decrease it. If you don't actively work to lower the churn rate, your company could suffer in the long-term.") 52 | st.subheader("1. Analyze churn to improve your customer service team.") 53 | st.write("Despite your best efforts, customer churn will happen and when it does, use it as an opportunity to dig into what led the customer to leave, and what you can do to prevent a similar customer from churning for the same reason.") 54 | st.write("One crucial step is to track your churn and retention rates. You can do this with HubSpot's Customer Service Metrics Calculator — a free tool to calculate and document your retention rate over time.") 55 | st.write("You can use instances of churn to dig into individual customer support rep or manager performance, analyze your product or service against competitors, or identify challenges in the customer experience that you want to remedy with the help of your product and development teams.") 56 | st.subheader("2. Revamp your onboarding plan for new customers.") 57 | st.write("You can work to prevent customer churn from the moment someone becomes a customer by creating a robust new onboarding process. Use a new customer welcome email and offer dedicated 1:1 and online customer onboarding. You can also create educational content on your blog, social media, and video channels to instruct customers and show them how to get optimal value from your product or service.") 58 | st.subheader("3. Invest in more training for support and sales reps.") 59 | st.write("Sales reps should be selling the true value of your product or service so customers don't feel swindled. Additionally, customer support employees should be well-equipped to manage any issue that comes their way to secure customer satisfaction. Investing in processes and resources for these two departments can have a drastic impact on churn rate.") 60 | st.subheader("4. Ask for feedback at key moments — and respond promptly.") 61 | st.write("Make sure you're constantly asking for customer feedback at key moments across the customer experience. If you've already identified that customers are likely to churn if they don't log into your tool every 15 days, ask them for feedback around day 10 and try to re-engage them.") 62 | st.write("If they hit a milestone using your product or service, ask them for feedback after that moment. Figure out the key moments that make or break a happy customer and ask for feedback at those touchpoints to strengthen the relationship.") 63 | st.write("Sometimes, customer feedback comes in the form of negative customer reviews — in which case you'll want to respond promptly and appropriately.") 64 | st.subheader("5. Communicate proactively with customers.") 65 | st.write("Build rapport with your customers by communicating with them proactively so they view you as a trusted partner. Periodically reach out with content you think they'll find interesting or helpful, connect and engage with them on social media, and reach out if issues or outages crop up on the product side so they know they can depend on you.") 66 | st.subheader("6. Offer exclusive perks to existing customers.") 67 | st.write("To prevent further churn, you can offer perks to your current customers. While you could potentially institute a reward program, that's a better fit for retail businesses. You can instead opt for personalized touch-points every once in a while, such as an in-person coffee chat or personal visit to their office.") 68 | st.write("If your business is small, you can also have the CEO personally check in with existing customers to find out how they're doing. This is also a great opportunity to get feedback. A busy customer may not take a survey, but if the CEO asks them if they have any comments, the customer may be more likely to respond.") 69 | st.subheader("7. Leverage feedback from free trial customers.") 70 | st.write("Churn doesn't happen until you lose revenue after a customer leaves your business. But if someone doesn't purchase your product after a free trial, that can be counted as churn — metaphorically speaking.") 71 | st.write("Carry out a survey of those who didn't purchase your product after a free trial. A customer who's already left the business likely won't answer many questions about your product or why it didn't work for them. Someone who took a free trial and ultimately didn't end up making a purchase will expect a survey link. They've also had little interaction with your business, so they're more likely to be frank.") 72 | st.write("Use this feedback to improve your product and learn what makes customers 'churn' before they even become a paying subscriber.") 73 | st.write("Pair these tips with customer retention strategies to lower churn rate.") 74 | st.subheader(":blue[8. Churn Rate Examples.]") 75 | st.write("Many SaaS companies, specifically in the B2C space, publish their churn rates to show how well they retain customers. Use these examples to guide your understanding of your own churn rate — what it should look like for your business and where some famous companies lie on the spectrum.") 76 | st.subheader("Netflix: 3.3% Monthly Churn Rate") 77 | st.write("Netflix has one of the lowest churn rates in the video streaming industry. Its monthly churn rate is strikingly low at 3.5%, meaning that just over 96% of customers choose to stay with Netflix. Causes may include its expansive catalog of shows and its well-established brand voice.") 78 | st.subheader("Disney+: 3.7% Monthly Churn Rate") 79 | st.write("Disney has always avoided being part of other streaming services, and it launched its own service to distribute its shows online. Disney+'s monthly churn rate is 5%, as of March 2023. Churn rates for the Disney Bundle, which includes Disney+, Hulu, and ESPN+, is even lower at just 2%.") 80 | st.subheader("Spotify: 3.9% Monthly Churn Rate") 81 | st.write("Spotify is a popular music streaming service that's known for its personalized recommendations and expansive music library. It has a reported churn rate of 3.9% at the end of 2021 according to CFO Paul Vogel.") 82 | st.subheader("Hulu: 5.2% Monthly Churn Rate") 83 | st.write("Hulu is one of Netflix's principal competitors. Well-known for its exclusive TV shows, it has an 11% market share in the video streaming industry and a 4.7% churn rate.") 84 | st.subheader("Peloton: 1.41% Monthly Churn Rate") 85 | st.write("Peloton has a 1.1% monthly churn rate. The exercise equipment and fitness subscription company may enjoy a high retention rate for being the first in-home cycling fitness subscription. Its status as the first of its kind has cemented its subscriber base.") 86 | st.subheader("Adobe: 10% Yearly Churn Rate") 87 | st.write("According to Rob Giglio, former Vice President of Adobe's Digital Media, Adobe has less than a 10% yearly churn rate and over a 90% customer retention rate.") 88 | st.subheader("Apple TV+: 15.6% Monthly Churn Rate") 89 | st.write("Apple TV+'s monthly churn rate is at 15.6%. Some outlets have reported that it's as high as 20%. A tech journalist called it the 'most unloved' of Apple's platforms. Another has argued that its catalog is 'tiny' and that the content is largely non-original. Additionally, many Apple users were on a free trial and Apple had been extending promotional periods since it launched, which may be the reason why its churn rate is higher compared to its competitors.") 90 | st.subheader(":blue[9. What is a good churn rate ?]") 91 | st.write("A good or 'acceptable' churn rate is from 2% to 8%, especially for B2C SaaS businesses that offer self-serve solutions. The lower, the better, or it can significantly impact your Monthly Recurring Revenue (MRR). For B2B SaaS businesses with high average contract values (greater than $1,000 per month), churn rate should be below 2%.") 92 | st.subheader(":blue[10. What is annual churn rate ?]") 93 | st.write("Annual churn rate refers to the percentage of customers lost over the course of a year. To calculate annual churn rate, you would look at the number of customers you had at the beginning of the year, then look at the number you had at the end of the year.") 94 | st.write("Subtract those two numbers. After, divide that by the amount of customers you had at the start of the year, and multiply by 100.") 95 | st.write("For example, let's say you had 1,000 customers at the beginning of the year and 800 at the end of the year.") 96 | st.write("(1,000 - 800) ÷ 1,000 x 100 = annual churn rate") 97 | st.write("(200) ÷ 1,000 x 100 = 20") 98 | st.write("The annual churn rate would be 20%.") 99 | st.subheader(":blue[11. What is monthly churn rate ?]") 100 | st.write("Monthly churn rate refers to the percentage of customers lost over the course of a month. To calculate monthly churn rate, divide the number of customers you lost over the month by the number of customers you had at the beginning of the month. Multiply the result by 100.") 101 | st.write("Let's try an example with real numbers. We'll go with 200 customers lost with 1,200 customers at the beginning of the month.") 102 | st.write("(200 ÷ 1,200) x 100 = monthly churn rate") 103 | st.write("0.16 x 100 = 16") 104 | st.write("The monthly churn rate is 16%.") 105 | st.subheader(":blue[12. What is revenue churn rate ?]") 106 | st.write("Revenue churn rate is a metric that measures the amount of revenue a business has lost due to customer churn during a given time period.") 107 | st.write("It's critical to keep an eye on your revenue churn rate because it directly affects the financial health of your business. If your company is losing a significant portion of its revenue due to customer churn or service downgrades, it can negatively impact your financial stability and profitability in the long term.") 108 | st.write("Revenue churn rate is also an important metric because it provides insight into the long-term value of your customers. If your revenue churn rate is too high, it could indicate that your customers are not finding enough value in your product or service, or that your retention efforts could be improved.") 109 | st.subheader(":blue[13. How to Calculate Revenue Churn Rate ?]") 110 | st.write("To calculate revenue churn rate, you need to know the revenue lost due to customer churn and the total revenue generated by your business during a specific time period. Divide the revenue lost due to customer churn by the total revenue generated. Then, multiply that number by 100 to get a percentage. Here's the formula:") 111 | st.write("Revenue churn rate = (Revenue lost due to customer churn / Total revenue generated) x 100") 112 | st.write("As an example, let's say your company generated 1 million in revenue in a month, and during that month lost $100,000 due to customer churn, the revenue churn rate would be calculated as follows:") 113 | st.write("Revenue Churn Rate = (100,000 ÷ 1,000,000) x 100") 114 | st.write("Revenue Churn Rate = (0.10) x 100") 115 | st.write("Revenue Churn Rate = 10%") 116 | st.subheader(":blue[14. Customer Churn Rate vs Revenue Churn Rate.]") 117 | st.write("Customer churn rate measures the percentage of customers who have stopped using your product or service, while revenue churn rate measures the percentage of revenue that has been lost due to customer churn.") 118 | st.write("Though customer churn rate and revenue churn rate are related, it's imperative to differentiate them because their results can mean very different things, especially for SaaS companies with multiple product tiers.") 119 | st.write("For example, if you notice a high customer churn rate, but revenue churn rate remains low, it might indicate that customers are downsizing to a lower-tier product rather than leaving altogether. On the flip side, if the revenue churn rate is high, but the customer churn rate is low, it might mean that the business is losing its largest customers.") 120 | st.write("By understanding both metrics, your business can take corrective action to improve customer retention rates and reduce churn, while protecting your revenue streams at the same time.") 121 | st.subheader(":blue[15. How can I track churn ?]") 122 | st.write("Tracking churn over time can be done in a number of ways. You can keep a spreadsheet with your findings and visualize it using the spreadsheet's built-in data visualization tool. You can also use a dedicated reporting dashboard software such as HubSpot's to automatically calculate and track churn.") 123 | st.subheader(":blue[16. What is the difference between attrition and churn ?]") 124 | st.write("Customer attrition is the same as customer churn. It's also referred to as customer turnover and customer defection.") 125 | st.write("Although the terms vary, they are all referring to churn and can be used interchangeably.") 126 | st.subheader(":blue[17. Calculate Churn Rate to Reduce Customer Turnover.]") 127 | st.write("Calculating churn rate may seem like an unpleasant task, but it's critical to track it to understand what may be going wrong on a customer service level. Calculate customer churn rate over a year or a month, improve your customer service systems, invest in your customer service reps, and watch your churn rate decrease exponentially.") 128 | -------------------------------------------------------------------------------- /Churn Analysis - Model Building.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "### Importing Libraries" 8 | ] 9 | }, 10 | { 11 | "cell_type": "code", 12 | "execution_count": 1, 13 | "metadata": {}, 14 | "outputs": [], 15 | "source": [ 16 | "import pandas as pd\n", 17 | "from sklearn import metrics\n", 18 | "from sklearn.model_selection import train_test_split\n", 19 | "from sklearn.metrics import recall_score\n", 20 | "from sklearn.metrics import classification_report\n", 21 | "from sklearn.metrics import confusion_matrix\n", 22 | "from sklearn.tree import DecisionTreeClassifier\n", 23 | "from imblearn.combine import SMOTEENN" 24 | ] 25 | }, 26 | { 27 | "cell_type": "markdown", 28 | "metadata": {}, 29 | "source": [ 30 | "#### Reading csv" 31 | ] 32 | }, 33 | { 34 | "cell_type": "code", 35 | "execution_count": 2, 36 | "metadata": {}, 37 | "outputs": [ 38 | { 39 | "data": { 40 | "text/html": [ 41 | "
\n", 42 | "\n", 55 | "\n", 56 | " \n", 57 | " \n", 58 | " \n", 59 | " \n", 60 | " \n", 61 | " \n", 62 | " \n", 63 | " \n", 64 | " \n", 65 | " \n", 66 | " \n", 67 | " \n", 68 | " \n", 69 | " \n", 70 | " \n", 71 | " \n", 72 | " \n", 73 | " \n", 74 | " \n", 75 | " \n", 76 | " \n", 77 | " \n", 78 | " \n", 79 | " \n", 80 | " \n", 81 | " \n", 82 | " \n", 83 | " \n", 84 | " \n", 85 | " \n", 86 | " \n", 87 | " \n", 88 | " \n", 89 | " \n", 90 | " \n", 91 | " \n", 92 | " \n", 93 | " \n", 94 | " \n", 95 | " \n", 96 | " \n", 97 | " \n", 98 | " \n", 99 | " \n", 100 | " \n", 101 | " \n", 102 | " \n", 103 | " \n", 104 | " \n", 105 | " \n", 106 | " \n", 107 | " \n", 108 | " \n", 109 | " \n", 110 | " \n", 111 | " \n", 112 | " \n", 113 | " \n", 114 | " \n", 115 | " \n", 116 | " \n", 117 | " \n", 118 | " \n", 119 | " \n", 120 | " \n", 121 | " \n", 122 | " \n", 123 | " \n", 124 | " \n", 125 | " \n", 126 | " \n", 127 | " \n", 128 | " \n", 129 | " \n", 130 | " \n", 131 | " \n", 132 | " \n", 133 | " \n", 134 | " \n", 135 | " \n", 136 | " \n", 137 | " \n", 138 | " \n", 139 | " \n", 140 | " \n", 141 | " \n", 142 | " \n", 143 | " \n", 144 | " \n", 145 | " \n", 146 | " \n", 147 | " \n", 148 | " \n", 149 | " \n", 150 | " \n", 151 | " \n", 152 | " \n", 153 | " \n", 154 | " \n", 155 | " \n", 156 | " \n", 157 | " \n", 158 | " \n", 159 | " \n", 160 | " \n", 161 | " \n", 162 | " \n", 163 | " \n", 164 | " \n", 165 | " \n", 166 | " \n", 167 | " \n", 168 | " \n", 169 | " \n", 170 | " \n", 171 | " \n", 172 | " \n", 173 | " \n", 174 | " \n", 175 | " \n", 176 | " \n", 177 | " \n", 178 | " \n", 179 | " \n", 180 | " \n", 181 | " \n", 182 | " \n", 183 | " \n", 184 | " \n", 185 | " \n", 186 | " \n", 187 | " \n", 188 | " \n", 189 | " \n", 190 | " \n", 191 | " \n", 192 | " \n", 193 | " \n", 194 | " \n", 195 | " \n", 196 | " \n", 197 | " \n", 198 | " \n", 199 | " \n", 200 | " \n", 201 | " \n", 202 | " \n", 203 | " \n", 204 | "
Unnamed: 0SeniorCitizenMonthlyChargesTotalChargesChurngender_Femalegender_MalePartner_NoPartner_YesDependents_No...PaymentMethod_Bank transfer (automatic)PaymentMethod_Credit card (automatic)PaymentMethod_Electronic checkPaymentMethod_Mailed checktenure_group_1 - 12tenure_group_13 - 24tenure_group_25 - 36tenure_group_37 - 48tenure_group_49 - 60tenure_group_61 - 72
00029.8529.85010011...0010100000
11056.951889.50001101...0001001000
22053.85108.15101101...0001100000
33042.301840.75001101...1000000100
44070.70151.65110101...0010100000
\n", 205 | "

5 rows × 52 columns

\n", 206 | "
" 207 | ], 208 | "text/plain": [ 209 | " Unnamed: 0 SeniorCitizen MonthlyCharges TotalCharges Churn \\\n", 210 | "0 0 0 29.85 29.85 0 \n", 211 | "1 1 0 56.95 1889.50 0 \n", 212 | "2 2 0 53.85 108.15 1 \n", 213 | "3 3 0 42.30 1840.75 0 \n", 214 | "4 4 0 70.70 151.65 1 \n", 215 | "\n", 216 | " gender_Female gender_Male Partner_No Partner_Yes Dependents_No ... \\\n", 217 | "0 1 0 0 1 1 ... \n", 218 | "1 0 1 1 0 1 ... \n", 219 | "2 0 1 1 0 1 ... \n", 220 | "3 0 1 1 0 1 ... \n", 221 | "4 1 0 1 0 1 ... \n", 222 | "\n", 223 | " PaymentMethod_Bank transfer (automatic) \\\n", 224 | "0 0 \n", 225 | "1 0 \n", 226 | "2 0 \n", 227 | "3 1 \n", 228 | "4 0 \n", 229 | "\n", 230 | " PaymentMethod_Credit card (automatic) PaymentMethod_Electronic check \\\n", 231 | "0 0 1 \n", 232 | "1 0 0 \n", 233 | "2 0 0 \n", 234 | "3 0 0 \n", 235 | "4 0 1 \n", 236 | "\n", 237 | " PaymentMethod_Mailed check tenure_group_1 - 12 tenure_group_13 - 24 \\\n", 238 | "0 0 1 0 \n", 239 | "1 1 0 0 \n", 240 | "2 1 1 0 \n", 241 | "3 0 0 0 \n", 242 | "4 0 1 0 \n", 243 | "\n", 244 | " tenure_group_25 - 36 tenure_group_37 - 48 tenure_group_49 - 60 \\\n", 245 | "0 0 0 0 \n", 246 | "1 1 0 0 \n", 247 | "2 0 0 0 \n", 248 | "3 0 1 0 \n", 249 | "4 0 0 0 \n", 250 | "\n", 251 | " tenure_group_61 - 72 \n", 252 | "0 0 \n", 253 | "1 0 \n", 254 | "2 0 \n", 255 | "3 0 \n", 256 | "4 0 \n", 257 | "\n", 258 | "[5 rows x 52 columns]" 259 | ] 260 | }, 261 | "execution_count": 2, 262 | "metadata": {}, 263 | "output_type": "execute_result" 264 | } 265 | ], 266 | "source": [ 267 | "df=pd.read_csv(\"tel_churn.csv\")\n", 268 | "df.head()" 269 | ] 270 | }, 271 | { 272 | "cell_type": "code", 273 | "execution_count": 3, 274 | "metadata": {}, 275 | "outputs": [], 276 | "source": [ 277 | "df=df.drop('Unnamed: 0',axis=1)" 278 | ] 279 | }, 280 | { 281 | "cell_type": "code", 282 | "execution_count": 4, 283 | "metadata": {}, 284 | "outputs": [ 285 | { 286 | "data": { 287 | "text/html": [ 288 | "
\n", 289 | "\n", 302 | "\n", 303 | " \n", 304 | " \n", 305 | " \n", 306 | " \n", 307 | " \n", 308 | " \n", 309 | " \n", 310 | " \n", 311 | " \n", 312 | " \n", 313 | " \n", 314 | " \n", 315 | " \n", 316 | " \n", 317 | " \n", 318 | " \n", 319 | " \n", 320 | " \n", 321 | " \n", 322 | " \n", 323 | " \n", 324 | " \n", 325 | " \n", 326 | " \n", 327 | " \n", 328 | " \n", 329 | " \n", 330 | " \n", 331 | " \n", 332 | " \n", 333 | " \n", 334 | " \n", 335 | " \n", 336 | " \n", 337 | " \n", 338 | " \n", 339 | " \n", 340 | " \n", 341 | " \n", 342 | " \n", 343 | " \n", 344 | " \n", 345 | " \n", 346 | " \n", 347 | " \n", 348 | " \n", 349 | " \n", 350 | " \n", 351 | " \n", 352 | " \n", 353 | " \n", 354 | " \n", 355 | " \n", 356 | " \n", 357 | " \n", 358 | " \n", 359 | " \n", 360 | " \n", 361 | " \n", 362 | " \n", 363 | " \n", 364 | " \n", 365 | " \n", 366 | " \n", 367 | " \n", 368 | " \n", 369 | " \n", 370 | " \n", 371 | " \n", 372 | " \n", 373 | " \n", 374 | " \n", 375 | " \n", 376 | " \n", 377 | " \n", 378 | " \n", 379 | " \n", 380 | " \n", 381 | " \n", 382 | " \n", 383 | " \n", 384 | " \n", 385 | " \n", 386 | " \n", 387 | " \n", 388 | " \n", 389 | " \n", 390 | " \n", 391 | " \n", 392 | " \n", 393 | " \n", 394 | " \n", 395 | " \n", 396 | " \n", 397 | " \n", 398 | " \n", 399 | " \n", 400 | " \n", 401 | " \n", 402 | " \n", 403 | " \n", 404 | " \n", 405 | " \n", 406 | " \n", 407 | " \n", 408 | " \n", 409 | " \n", 410 | " \n", 411 | " \n", 412 | " \n", 413 | " \n", 414 | " \n", 415 | " \n", 416 | " \n", 417 | " \n", 418 | " \n", 419 | " \n", 420 | " \n", 421 | " \n", 422 | " \n", 423 | " \n", 424 | " \n", 425 | " \n", 426 | " \n", 427 | " \n", 428 | " \n", 429 | " \n", 430 | " \n", 431 | " \n", 432 | " \n", 433 | " \n", 434 | " \n", 435 | " \n", 436 | " \n", 437 | " \n", 438 | " \n", 439 | " \n", 440 | " \n", 441 | " \n", 442 | " \n", 443 | " \n", 444 | " \n", 445 | " \n", 446 | " \n", 447 | " \n", 448 | " \n", 449 | " \n", 450 | " \n", 451 | " \n", 452 | " \n", 453 | " \n", 454 | " \n", 455 | " \n", 456 | " \n", 457 | " \n", 458 | " \n", 459 | " \n", 460 | " \n", 461 | " \n", 462 | " \n", 463 | " \n", 464 | " \n", 465 | " \n", 466 | " \n", 467 | " \n", 468 | " \n", 469 | " \n", 470 | " \n", 471 | " \n", 472 | " \n", 473 | " \n", 474 | " \n", 475 | " \n", 476 | " \n", 477 | " \n", 478 | " \n", 479 | " \n", 480 | " \n", 481 | " \n", 482 | " \n", 483 | " \n", 484 | " \n", 485 | " \n", 486 | " \n", 487 | " \n", 488 | " \n", 489 | " \n", 490 | " \n", 491 | " \n", 492 | " \n", 493 | " \n", 494 | " \n", 495 | " \n", 496 | " \n", 497 | " \n", 498 | " \n", 499 | " \n", 500 | " \n", 501 | " \n", 502 | " \n", 503 | " \n", 504 | " \n", 505 | " \n", 506 | " \n", 507 | " \n", 508 | " \n", 509 | " \n", 510 | " \n", 511 | " \n", 512 | " \n", 513 | " \n", 514 | " \n", 515 | " \n", 516 | " \n", 517 | " \n", 518 | " \n", 519 | " \n", 520 | " \n", 521 | " \n", 522 | " \n", 523 | " \n", 524 | " \n", 525 | " \n", 526 | " \n", 527 | " \n", 528 | " \n", 529 | " \n", 530 | " \n", 531 | " \n", 532 | " \n", 533 | " \n", 534 | " \n", 535 | " \n", 536 | " \n", 537 | " \n", 538 | " \n", 539 | " \n", 540 | " \n", 541 | " \n", 542 | " \n", 543 | " \n", 544 | " \n", 545 | " \n", 546 | " \n", 547 | " \n", 548 | " \n", 549 | " \n", 550 | " \n", 551 | " \n", 552 | " \n", 553 | " \n", 554 | " \n", 555 | " \n", 556 | " \n", 557 | " \n", 558 | " \n", 559 | " \n", 560 | " \n", 561 | " \n", 562 | " \n", 563 | " \n", 564 | " \n", 565 | " \n", 566 | " \n", 567 | " \n", 568 | " \n", 569 | " \n", 570 | " \n", 571 | " \n", 572 | " \n", 573 | " \n", 574 | " \n", 575 | " \n", 576 | " \n", 577 | " \n", 578 | " \n", 579 | " \n", 580 | " \n", 581 | " \n", 582 | " \n", 583 | " \n", 584 | " \n", 585 | " \n", 586 | " \n", 587 | " \n", 588 | " \n", 589 | " \n", 590 | " \n", 591 | " \n", 592 | " \n", 593 | " \n", 594 | " \n", 595 | " \n", 596 | " \n", 597 | " \n", 598 | " \n", 599 | " \n", 600 | " \n", 601 | " \n", 602 | " \n", 603 | " \n", 604 | " \n", 605 | " \n", 606 | " \n", 607 | " \n", 608 | " \n", 609 | " \n", 610 | " \n", 611 | " \n", 612 | " \n", 613 | " \n", 614 | " \n", 615 | " \n", 616 | " \n", 617 | " \n", 618 | " \n", 619 | " \n", 620 | " \n", 621 | " \n", 622 | " \n", 623 | " \n", 624 | " \n", 625 | " \n", 626 | " \n", 627 | " \n", 628 | " \n", 629 | " \n", 630 | " \n", 631 | " \n", 632 | " \n", 633 | " \n", 634 | " \n", 635 | " \n", 636 | " \n", 637 | " \n", 638 | " \n", 639 | " \n", 640 | " \n", 641 | " \n", 642 | " \n", 643 | " \n", 644 | " \n", 645 | " \n", 646 | " \n", 647 | " \n", 648 | " \n", 649 | " \n", 650 | " \n", 651 | " \n", 652 | " \n", 653 | " \n", 654 | " \n", 655 | " \n", 656 | " \n", 657 | " \n", 658 | " \n", 659 | " \n", 660 | " \n", 661 | " \n", 662 | " \n", 663 | " \n", 664 | " \n", 665 | " \n", 666 | " \n", 667 | " \n", 668 | " \n", 669 | " \n", 670 | " \n", 671 | " \n", 672 | " \n", 673 | " \n", 674 | " \n", 675 | " \n", 676 | " \n", 677 | " \n", 678 | " \n", 679 | " \n", 680 | " \n", 681 | " \n", 682 | " \n", 683 | " \n", 684 | " \n", 685 | " \n", 686 | " \n", 687 | " \n", 688 | " \n", 689 | " \n", 690 | " \n", 691 | " \n", 692 | " \n", 693 | " \n", 694 | " \n", 695 | " \n", 696 | " \n", 697 | " \n", 698 | " \n", 699 | " \n", 700 | " \n", 701 | " \n", 702 | " \n", 703 | " \n", 704 | " \n", 705 | " \n", 706 | " \n", 707 | " \n", 708 | " \n", 709 | " \n", 710 | " \n", 711 | " \n", 712 | " \n", 713 | " \n", 714 | " \n", 715 | " \n", 716 | " \n", 717 | " \n", 718 | " \n", 719 | " \n", 720 | " \n", 721 | " \n", 722 | " \n", 723 | " \n", 724 | " \n", 725 | " \n", 726 | " \n", 727 | " \n", 728 | " \n", 729 | " \n", 730 | " \n", 731 | " \n", 732 | " \n", 733 | " \n", 734 | " \n", 735 | " \n", 736 | " \n", 737 | " \n", 738 | " \n", 739 | " \n", 740 | " \n", 741 | " \n", 742 | " \n", 743 | " \n", 744 | " \n", 745 | " \n", 746 | " \n", 747 | " \n", 748 | " \n", 749 | " \n", 750 | " \n", 751 | " \n", 752 | " \n", 753 | " \n", 754 | " \n", 755 | " \n", 756 | " \n", 757 | " \n", 758 | " \n", 759 | " \n", 760 | " \n", 761 | " \n", 762 | " \n", 763 | " \n", 764 | " \n", 765 | " \n", 766 | " \n", 767 | " \n", 768 | " \n", 769 | " \n", 770 | " \n", 771 | " \n", 772 | " \n", 773 | " \n", 774 | " \n", 775 | " \n", 776 | " \n", 777 | " \n", 778 | " \n", 779 | " \n", 780 | " \n", 781 | " \n", 782 | " \n", 783 | " \n", 784 | " \n", 785 | " \n", 786 | " \n", 787 | " \n", 788 | " \n", 789 | " \n", 790 | " \n", 791 | " \n", 792 | " \n", 793 | " \n", 794 | " \n", 795 | " \n", 796 | " \n", 797 | " \n", 798 | " \n", 799 | " \n", 800 | " \n", 801 | " \n", 802 | " \n", 803 | " \n", 804 | " \n", 805 | " \n", 806 | " \n", 807 | " \n", 808 | " \n", 809 | " \n", 810 | " \n", 811 | " \n", 812 | " \n", 813 | " \n", 814 | " \n", 815 | " \n", 816 | " \n", 817 | " \n", 818 | " \n", 819 | " \n", 820 | " \n", 821 | " \n", 822 | " \n", 823 | " \n", 824 | " \n", 825 | " \n", 826 | " \n", 827 | " \n", 828 | " \n", 829 | " \n", 830 | " \n", 831 | " \n", 832 | " \n", 833 | " \n", 834 | " \n", 835 | " \n", 836 | " \n", 837 | " \n", 838 | " \n", 839 | " \n", 840 | " \n", 841 | " \n", 842 | " \n", 843 | " \n", 844 | " \n", 845 | " \n", 846 | " \n", 847 | " \n", 848 | " \n", 849 | " \n", 850 | " \n", 851 | " \n", 852 | " \n", 853 | " \n", 854 | " \n", 855 | " \n", 856 | " \n", 857 | " \n", 858 | " \n", 859 | " \n", 860 | " \n", 861 | " \n", 862 | " \n", 863 | " \n", 864 | " \n", 865 | " \n", 866 | " \n", 867 | " \n", 868 | " \n", 869 | " \n", 870 | " \n", 871 | " \n", 872 | " \n", 873 | " \n", 874 | " \n", 875 | " \n", 876 | " \n", 877 | " \n", 878 | " \n", 879 | " \n", 880 | " \n", 881 | " \n", 882 | " \n", 883 | " \n", 884 | " \n", 885 | " \n", 886 | " \n", 887 | " \n", 888 | " \n", 889 | " \n", 890 | " \n", 891 | " \n", 892 | " \n", 893 | " \n", 894 | " \n", 895 | " \n", 896 | " \n", 897 | " \n", 898 | " \n", 899 | " \n", 900 | " \n", 901 | " \n", 902 | " \n", 903 | " \n", 904 | " \n", 905 | " \n", 906 | " \n", 907 | " \n", 908 | " \n", 909 | " \n", 910 | " \n", 911 | " \n", 912 | " \n", 913 | " \n", 914 | " \n", 915 | " \n", 916 | " \n", 917 | " \n", 918 | " \n", 919 | " \n", 920 | " \n", 921 | " \n", 922 | " \n", 923 | " \n", 924 | " \n", 925 | " \n", 926 | " \n", 927 | " \n", 928 | " \n", 929 | " \n", 930 | " \n", 931 | " \n", 932 | " \n", 933 | " \n", 934 | " \n", 935 | " \n", 936 | " \n", 937 | " \n", 938 | " \n", 939 | " \n", 940 | " \n", 941 | " \n", 942 | " \n", 943 | " \n", 944 | " \n", 945 | " \n", 946 | " \n", 947 | " \n", 948 | " \n", 949 | " \n", 950 | " \n", 951 | " \n", 952 | " \n", 953 | " \n", 954 | " \n", 955 | " \n", 956 | " \n", 957 | " \n", 958 | " \n", 959 | " \n", 960 | " \n", 961 | " \n", 962 | " \n", 963 | " \n", 964 | " \n", 965 | " \n", 966 | " \n", 967 | " \n", 968 | " \n", 969 | " \n", 970 | " \n", 971 | " \n", 972 | " \n", 973 | " \n", 974 | " \n", 975 | " \n", 976 | " \n", 977 | " \n", 978 | " \n", 979 | " \n", 980 | " \n", 981 | " \n", 982 | " \n", 983 | " \n", 984 | " \n", 985 | " \n", 986 | " \n", 987 | " \n", 988 | " \n", 989 | " \n", 990 | " \n", 991 | " \n", 992 | " \n", 993 | " \n", 994 | " \n", 995 | " \n", 996 | " \n", 997 | " \n", 998 | " \n", 999 | " \n", 1000 | " \n", 1001 | " \n", 1002 | " \n", 1003 | " \n", 1004 | " \n", 1005 | " \n", 1006 | " \n", 1007 | " \n", 1008 | " \n", 1009 | " \n", 1010 | " \n", 1011 | " \n", 1012 | " \n", 1013 | " \n", 1014 | " \n", 1015 | " \n", 1016 | " \n", 1017 | " \n", 1018 | " \n", 1019 | " \n", 1020 | " \n", 1021 | " \n", 1022 | " \n", 1023 | " \n", 1024 | " \n", 1025 | " \n", 1026 | " \n", 1027 | " \n", 1028 | " \n", 1029 | " \n", 1030 | " \n", 1031 | " \n", 1032 | " \n", 1033 | " \n", 1034 | " \n", 1035 | " \n", 1036 | " \n", 1037 | " \n", 1038 | " \n", 1039 | " \n", 1040 | " \n", 1041 | " \n", 1042 | " \n", 1043 | " \n", 1044 | " \n", 1045 | " \n", 1046 | " \n", 1047 | " \n", 1048 | " \n", 1049 | " \n", 1050 | " \n", 1051 | " \n", 1052 | " \n", 1053 | " \n", 1054 | " \n", 1055 | " \n", 1056 | " \n", 1057 | " \n", 1058 | " \n", 1059 | " \n", 1060 | " \n", 1061 | " \n", 1062 | " \n", 1063 | " \n", 1064 | " \n", 1065 | " \n", 1066 | " \n", 1067 | " \n", 1068 | " \n", 1069 | " \n", 1070 | " \n", 1071 | " \n", 1072 | " \n", 1073 | " \n", 1074 | " \n", 1075 | " \n", 1076 | " \n", 1077 | " \n", 1078 | " \n", 1079 | " \n", 1080 | " \n", 1081 | " \n", 1082 | " \n", 1083 | " \n", 1084 | " \n", 1085 | " \n", 1086 | " \n", 1087 | " \n", 1088 | " \n", 1089 | " \n", 1090 | " \n", 1091 | " \n", 1092 | " \n", 1093 | " \n", 1094 | " \n", 1095 | " \n", 1096 | " \n", 1097 | " \n", 1098 | " \n", 1099 | " \n", 1100 | " \n", 1101 | " \n", 1102 | " \n", 1103 | " \n", 1104 | " \n", 1105 | " \n", 1106 | " \n", 1107 | " \n", 1108 | " \n", 1109 | " \n", 1110 | " \n", 1111 | " \n", 1112 | " \n", 1113 | " \n", 1114 | " \n", 1115 | " \n", 1116 | " \n", 1117 | " \n", 1118 | " \n", 1119 | " \n", 1120 | " \n", 1121 | " \n", 1122 | " \n", 1123 | " \n", 1124 | " \n", 1125 | " \n", 1126 | " \n", 1127 | " \n", 1128 | " \n", 1129 | " \n", 1130 | " \n", 1131 | " \n", 1132 | " \n", 1133 | " \n", 1134 | " \n", 1135 | " \n", 1136 | " \n", 1137 | " \n", 1138 | " \n", 1139 | " \n", 1140 | " \n", 1141 | " \n", 1142 | " \n", 1143 | " \n", 1144 | " \n", 1145 | " \n", 1146 | " \n", 1147 | " \n", 1148 | " \n", 1149 | " \n", 1150 | " \n", 1151 | " \n", 1152 | " \n", 1153 | " \n", 1154 | " \n", 1155 | " \n", 1156 | " \n", 1157 | " \n", 1158 | " \n", 1159 | " \n", 1160 | " \n", 1161 | " \n", 1162 | " \n", 1163 | " \n", 1164 | " \n", 1165 | " \n", 1166 | " \n", 1167 | " \n", 1168 | " \n", 1169 | " \n", 1170 | " \n", 1171 | " \n", 1172 | " \n", 1173 | " \n", 1174 | " \n", 1175 | " \n", 1176 | " \n", 1177 | " \n", 1178 | " \n", 1179 | " \n", 1180 | " \n", 1181 | " \n", 1182 | " \n", 1183 | " \n", 1184 | " \n", 1185 | " \n", 1186 | " \n", 1187 | " \n", 1188 | " \n", 1189 | " \n", 1190 | " \n", 1191 | " \n", 1192 | " \n", 1193 | " \n", 1194 | " \n", 1195 | " \n", 1196 | " \n", 1197 | " \n", 1198 | " \n", 1199 | " \n", 1200 | " \n", 1201 | " \n", 1202 | " \n", 1203 | " \n", 1204 | " \n", 1205 | " \n", 1206 | " \n", 1207 | " \n", 1208 | " \n", 1209 | " \n", 1210 | " \n", 1211 | " \n", 1212 | " \n", 1213 | " \n", 1214 | " \n", 1215 | " \n", 1216 | " \n", 1217 | " \n", 1218 | " \n", 1219 | " \n", 1220 | " \n", 1221 | " \n", 1222 | " \n", 1223 | " \n", 1224 | " \n", 1225 | " \n", 1226 | " \n", 1227 | " \n", 1228 | " \n", 1229 | " \n", 1230 | " \n", 1231 | " \n", 1232 | " \n", 1233 | " \n", 1234 | " \n", 1235 | " \n", 1236 | " \n", 1237 | " \n", 1238 | " \n", 1239 | " \n", 1240 | " \n", 1241 | " \n", 1242 | " \n", 1243 | " \n", 1244 | " \n", 1245 | " \n", 1246 | " \n", 1247 | " \n", 1248 | " \n", 1249 | " \n", 1250 | " \n", 1251 | " \n", 1252 | " \n", 1253 | " \n", 1254 | " \n", 1255 | " \n", 1256 | " \n", 1257 | " \n", 1258 | " \n", 1259 | " \n", 1260 | " \n", 1261 | " \n", 1262 | " \n", 1263 | " \n", 1264 | " \n", 1265 | " \n", 1266 | " \n", 1267 | " \n", 1268 | " \n", 1269 | " \n", 1270 | " \n", 1271 | " \n", 1272 | " \n", 1273 | " \n", 1274 | " \n", 1275 | " \n", 1276 | " \n", 1277 | " \n", 1278 | " \n", 1279 | " \n", 1280 | " \n", 1281 | " \n", 1282 | " \n", 1283 | " \n", 1284 | " \n", 1285 | " \n", 1286 | " \n", 1287 | " \n", 1288 | " \n", 1289 | " \n", 1290 | " \n", 1291 | " \n", 1292 | " \n", 1293 | " \n", 1294 | " \n", 1295 | " \n", 1296 | " \n", 1297 | " \n", 1298 | " \n", 1299 | " \n", 1300 | " \n", 1301 | " \n", 1302 | " \n", 1303 | " \n", 1304 | " \n", 1305 | " \n", 1306 | " \n", 1307 | " \n", 1308 | " \n", 1309 | " \n", 1310 | " \n", 1311 | " \n", 1312 | " \n", 1313 | " \n", 1314 | " \n", 1315 | " \n", 1316 | " \n", 1317 | " \n", 1318 | " \n", 1319 | " \n", 1320 | " \n", 1321 | " \n", 1322 | " \n", 1323 | " \n", 1324 | " \n", 1325 | " \n", 1326 | " \n", 1327 | " \n", 1328 | " \n", 1329 | " \n", 1330 | " \n", 1331 | " \n", 1332 | " \n", 1333 | " \n", 1334 | " \n", 1335 | " \n", 1336 | " \n", 1337 | " \n", 1338 | " \n", 1339 | " \n", 1340 | " \n", 1341 | " \n", 1342 | " \n", 1343 | " \n", 1344 | " \n", 1345 | " \n", 1346 | " \n", 1347 | " \n", 1348 | " \n", 1349 | " \n", 1350 | " \n", 1351 | " \n", 1352 | " \n", 1353 | " \n", 1354 | " \n", 1355 | " \n", 1356 | " \n", 1357 | " \n", 1358 | " \n", 1359 | " \n", 1360 | " \n", 1361 | " \n", 1362 | " \n", 1363 | " \n", 1364 | " \n", 1365 | " \n", 1366 | " \n", 1367 | " \n", 1368 | " \n", 1369 | " \n", 1370 | " \n", 1371 | " \n", 1372 | " \n", 1373 | " \n", 1374 | " \n", 1375 | " \n", 1376 | " \n", 1377 | " \n", 1378 | " \n", 1379 | " \n", 1380 | " \n", 1381 | " \n", 1382 | " \n", 1383 | " \n", 1384 | " \n", 1385 | " \n", 1386 | " \n", 1387 | " \n", 1388 | " \n", 1389 | " \n", 1390 | " \n", 1391 | " \n", 1392 | " \n", 1393 | " \n", 1394 | " \n", 1395 | " \n", 1396 | " \n", 1397 | " \n", 1398 | " \n", 1399 | " \n", 1400 | " \n", 1401 | " \n", 1402 | " \n", 1403 | " \n", 1404 | " \n", 1405 | " \n", 1406 | " \n", 1407 | " \n", 1408 | " \n", 1409 | " \n", 1410 | " \n", 1411 | " \n", 1412 | " \n", 1413 | " \n", 1414 | " \n", 1415 | " \n", 1416 | " \n", 1417 | " \n", 1418 | " \n", 1419 | " \n", 1420 | " \n", 1421 | " \n", 1422 | " \n", 1423 | " \n", 1424 | " \n", 1425 | " \n", 1426 | " \n", 1427 | " \n", 1428 | " \n", 1429 | " \n", 1430 | " \n", 1431 | " \n", 1432 | " \n", 1433 | " \n", 1434 | " \n", 1435 | " \n", 1436 | " \n", 1437 | " \n", 1438 | " \n", 1439 | " \n", 1440 | " \n", 1441 | " \n", 1442 | " \n", 1443 | " \n", 1444 | " \n", 1445 | " \n", 1446 | " \n", 1447 | " \n", 1448 | " \n", 1449 | " \n", 1450 | " \n", 1451 | " \n", 1452 | " \n", 1453 | " \n", 1454 | " \n", 1455 | " \n", 1456 | " \n", 1457 | " \n", 1458 | " \n", 1459 | " \n", 1460 | " \n", 1461 | " \n", 1462 | " \n", 1463 | " \n", 1464 | " \n", 1465 | " \n", 1466 | " \n", 1467 | " \n", 1468 | " \n", 1469 | " \n", 1470 | " \n", 1471 | " \n", 1472 | " \n", 1473 | " \n", 1474 | " \n", 1475 | " \n", 1476 | " \n", 1477 | " \n", 1478 | " \n", 1479 | " \n", 1480 | " \n", 1481 | " \n", 1482 | " \n", 1483 | " \n", 1484 | " \n", 1485 | " \n", 1486 | " \n", 1487 | " \n", 1488 | " \n", 1489 | " \n", 1490 | " \n", 1491 | " \n", 1492 | " \n", 1493 | " \n", 1494 | " \n", 1495 | " \n", 1496 | " \n", 1497 | " \n", 1498 | " \n", 1499 | " \n", 1500 | " \n", 1501 | " \n", 1502 | " \n", 1503 | " \n", 1504 | " \n", 1505 | " \n", 1506 | " \n", 1507 | " \n", 1508 | " \n", 1509 | " \n", 1510 | " \n", 1511 | " \n", 1512 | " \n", 1513 | " \n", 1514 | " \n", 1515 | " \n", 1516 | " \n", 1517 | " \n", 1518 | " \n", 1519 | " \n", 1520 | " \n", 1521 | " \n", 1522 | " \n", 1523 | " \n", 1524 | " \n", 1525 | " \n", 1526 | " \n", 1527 | " \n", 1528 | " \n", 1529 | " \n", 1530 | " \n", 1531 | " \n", 1532 | " \n", 1533 | " \n", 1534 | " \n", 1535 | " \n", 1536 | " \n", 1537 | " \n", 1538 | " \n", 1539 | " \n", 1540 | " \n", 1541 | " \n", 1542 | " \n", 1543 | " \n", 1544 | " \n", 1545 | " \n", 1546 | " \n", 1547 | " \n", 1548 | " \n", 1549 | " \n", 1550 | " \n", 1551 | " \n", 1552 | " \n", 1553 | " \n", 1554 | " \n", 1555 | " \n", 1556 | " \n", 1557 | " \n", 1558 | " \n", 1559 | " \n", 1560 | " \n", 1561 | " \n", 1562 | " \n", 1563 | " \n", 1564 | " \n", 1565 | " \n", 1566 | " \n", 1567 | " \n", 1568 | " \n", 1569 | " \n", 1570 | " \n", 1571 | " \n", 1572 | " \n", 1573 | " \n", 1574 | " \n", 1575 | " \n", 1576 | " \n", 1577 | " \n", 1578 | " \n", 1579 | " \n", 1580 | " \n", 1581 | " \n", 1582 | " \n", 1583 | " \n", 1584 | " \n", 1585 | " \n", 1586 | " \n", 1587 | " \n", 1588 | " \n", 1589 | " \n", 1590 | " \n", 1591 | " \n", 1592 | " \n", 1593 | " \n", 1594 | " \n", 1595 | " \n", 1596 | " \n", 1597 | " \n", 1598 | " \n", 1599 | " \n", 1600 | " \n", 1601 | " \n", 1602 | " \n", 1603 | " \n", 1604 | " \n", 1605 | " \n", 1606 | " \n", 1607 | " \n", 1608 | " \n", 1609 | " \n", 1610 | " \n", 1611 | " \n", 1612 | " \n", 1613 | " \n", 1614 | " \n", 1615 | " \n", 1616 | " \n", 1617 | " \n", 1618 | " \n", 1619 | " \n", 1620 | " \n", 1621 | " \n", 1622 | " \n", 1623 | " \n", 1624 | " \n", 1625 | " \n", 1626 | " \n", 1627 | " \n", 1628 | " \n", 1629 | " \n", 1630 | " \n", 1631 | " \n", 1632 | " \n", 1633 | " \n", 1634 | " \n", 1635 | " \n", 1636 | " \n", 1637 | " \n", 1638 | " \n", 1639 | " \n", 1640 | " \n", 1641 | " \n", 1642 | " \n", 1643 | " \n", 1644 | " \n", 1645 | " \n", 1646 | " \n", 1647 | " \n", 1648 | " \n", 1649 | " \n", 1650 | " \n", 1651 | " \n", 1652 | " \n", 1653 | " \n", 1654 | " \n", 1655 | " \n", 1656 | " \n", 1657 | " \n", 1658 | " \n", 1659 | " \n", 1660 | " \n", 1661 | " \n", 1662 | " \n", 1663 | " \n", 1664 | " \n", 1665 | " \n", 1666 | " \n", 1667 | " \n", 1668 | " \n", 1669 | " \n", 1670 | " \n", 1671 | " \n", 1672 | " \n", 1673 | " \n", 1674 | " \n", 1675 | " \n", 1676 | " \n", 1677 | " \n", 1678 | " \n", 1679 | " \n", 1680 | " \n", 1681 | " \n", 1682 | " \n", 1683 | " \n", 1684 | " \n", 1685 | " \n", 1686 | " \n", 1687 | " \n", 1688 | " \n", 1689 | " \n", 1690 | " \n", 1691 | " \n", 1692 | " \n", 1693 | " \n", 1694 | " \n", 1695 | " \n", 1696 | " \n", 1697 | " \n", 1698 | " \n", 1699 | " \n", 1700 | " \n", 1701 | " \n", 1702 | " \n", 1703 | " \n", 1704 | " \n", 1705 | " \n", 1706 | " \n", 1707 | " \n", 1708 | " \n", 1709 | " \n", 1710 | " \n", 1711 | " \n", 1712 | " \n", 1713 | " \n", 1714 | " \n", 1715 | " \n", 1716 | " \n", 1717 | " \n", 1718 | " \n", 1719 | " \n", 1720 | " \n", 1721 | " \n", 1722 | " \n", 1723 | " \n", 1724 | " \n", 1725 | " \n", 1726 | " \n", 1727 | " \n", 1728 | " \n", 1729 | " \n", 1730 | " \n", 1731 | " \n", 1732 | " \n", 1733 | " \n", 1734 | " \n", 1735 | " \n", 1736 | " \n", 1737 | " \n", 1738 | " \n", 1739 | " \n", 1740 | " \n", 1741 | " \n", 1742 | " \n", 1743 | " \n", 1744 | " \n", 1745 | " \n", 1746 | " \n", 1747 | " \n", 1748 | " \n", 1749 | " \n", 1750 | " \n", 1751 | " \n", 1752 | " \n", 1753 | " \n", 1754 | " \n", 1755 | " \n", 1756 | " \n", 1757 | " \n", 1758 | " \n", 1759 | " \n", 1760 | " \n", 1761 | " \n", 1762 | " \n", 1763 | " \n", 1764 | " \n", 1765 | " \n", 1766 | " \n", 1767 | " \n", 1768 | " \n", 1769 | " \n", 1770 | " \n", 1771 | " \n", 1772 | " \n", 1773 | " \n", 1774 | " \n", 1775 | " \n", 1776 | " \n", 1777 | " \n", 1778 | " \n", 1779 | " \n", 1780 | " \n", 1781 | " \n", 1782 | " \n", 1783 | " \n", 1784 | " \n", 1785 | " \n", 1786 | " \n", 1787 | " \n", 1788 | " \n", 1789 | " \n", 1790 | " \n", 1791 | " \n", 1792 | " \n", 1793 | " \n", 1794 | " \n", 1795 | "
SeniorCitizenMonthlyChargesTotalChargesgender_Femalegender_MalePartner_NoPartner_YesDependents_NoDependents_YesPhoneService_No...PaymentMethod_Bank transfer (automatic)PaymentMethod_Credit card (automatic)PaymentMethod_Electronic checkPaymentMethod_Mailed checktenure_group_1 - 12tenure_group_13 - 24tenure_group_25 - 36tenure_group_37 - 48tenure_group_49 - 60tenure_group_61 - 72
0029.8529.851001101...0010100000
1056.951889.500110100...0001001000
2053.85108.150110100...0001100000
3042.301840.750110101...1000000100
4070.70151.651010100...0010100000
5099.65820.501010100...0010100000
6089.101949.400110010...0100010000
7029.75301.901010101...0001100000
80104.803046.051001100...0010001000
9056.153487.950110010...1000000001
10049.95587.450101010...0001010000
11018.95326.800110100...0100010000
120100.355681.100101100...0100000010
130103.705036.300110100...1000000010
140105.502686.050110100...0010001000
150113.257895.151001010...0100000001
16020.651022.951010100...0001000010
170106.707382.250110010...1000000001
18055.20528.351001010...0100100000
19090.051862.901010100...0010010000
20139.6539.650110101...0010100000
21019.80202.250101100...1000100000
22020.1520.150110100...0001100000
23059.903505.101001100...0100000010
24059.602970.300101010...0100000010
25055.301530.601010100...1000001000
26099.354749.150101010...0010000100
27030.2030.200101011...0010100000
28090.256369.450101100...0100000001
29064.701093.101010010...0001010000
..................................................................
7002093.403756.401010100...1000000100
7003089.203645.750110100...0010000100
7004185.202874.450101100...0100001000
7005049.9549.951010100...0010100000
7006020.651020.751010100...1000000010
7007070.6570.650101010...0001100000
7008020.15826.001010100...0001000100
7009019.20239.000101010...0010100000
7010059.80727.800110100...0010100000
70110104.957544.300110100...0010000001
70121103.506479.401001100...0010000001
7013084.803626.350101100...0100000100
7014095.051679.401010100...1000010000
7015044.20403.351010100...1000100000
7016073.35931.550110100...0001010000
7017064.104326.251001100...1000000001
7018144.40263.051010101...0010100000
7019020.0539.251010100...0001100000
7020160.003316.100101100...0100000010
7021175.7575.750110100...0010100000
7022069.502625.250110100...0100000100
70230102.956886.251010100...0100000001
7024078.701495.100110100...1000010000
7025060.65743.301010101...0010100000
7026021.151419.401010100...1000000001
7027084.801990.500101010...0001010000
70280103.207362.901001010...0100000001
7029029.60346.451001011...0010100000
7030174.40306.600101100...0001100000
70310105.656844.500110100...1000000001
\n", 1796 | "

7032 rows × 50 columns

\n", 1797 | "
" 1798 | ], 1799 | "text/plain": [ 1800 | " SeniorCitizen MonthlyCharges TotalCharges gender_Female gender_Male \\\n", 1801 | "0 0 29.85 29.85 1 0 \n", 1802 | "1 0 56.95 1889.50 0 1 \n", 1803 | "2 0 53.85 108.15 0 1 \n", 1804 | "3 0 42.30 1840.75 0 1 \n", 1805 | "4 0 70.70 151.65 1 0 \n", 1806 | "5 0 99.65 820.50 1 0 \n", 1807 | "6 0 89.10 1949.40 0 1 \n", 1808 | "7 0 29.75 301.90 1 0 \n", 1809 | "8 0 104.80 3046.05 1 0 \n", 1810 | "9 0 56.15 3487.95 0 1 \n", 1811 | "10 0 49.95 587.45 0 1 \n", 1812 | "11 0 18.95 326.80 0 1 \n", 1813 | "12 0 100.35 5681.10 0 1 \n", 1814 | "13 0 103.70 5036.30 0 1 \n", 1815 | "14 0 105.50 2686.05 0 1 \n", 1816 | "15 0 113.25 7895.15 1 0 \n", 1817 | "16 0 20.65 1022.95 1 0 \n", 1818 | "17 0 106.70 7382.25 0 1 \n", 1819 | "18 0 55.20 528.35 1 0 \n", 1820 | "19 0 90.05 1862.90 1 0 \n", 1821 | "20 1 39.65 39.65 0 1 \n", 1822 | "21 0 19.80 202.25 0 1 \n", 1823 | "22 0 20.15 20.15 0 1 \n", 1824 | "23 0 59.90 3505.10 1 0 \n", 1825 | "24 0 59.60 2970.30 0 1 \n", 1826 | "25 0 55.30 1530.60 1 0 \n", 1827 | "26 0 99.35 4749.15 0 1 \n", 1828 | "27 0 30.20 30.20 0 1 \n", 1829 | "28 0 90.25 6369.45 0 1 \n", 1830 | "29 0 64.70 1093.10 1 0 \n", 1831 | "... ... ... ... ... ... \n", 1832 | "7002 0 93.40 3756.40 1 0 \n", 1833 | "7003 0 89.20 3645.75 0 1 \n", 1834 | "7004 1 85.20 2874.45 0 1 \n", 1835 | "7005 0 49.95 49.95 1 0 \n", 1836 | "7006 0 20.65 1020.75 1 0 \n", 1837 | "7007 0 70.65 70.65 0 1 \n", 1838 | "7008 0 20.15 826.00 1 0 \n", 1839 | "7009 0 19.20 239.00 0 1 \n", 1840 | "7010 0 59.80 727.80 0 1 \n", 1841 | "7011 0 104.95 7544.30 0 1 \n", 1842 | "7012 1 103.50 6479.40 1 0 \n", 1843 | "7013 0 84.80 3626.35 0 1 \n", 1844 | "7014 0 95.05 1679.40 1 0 \n", 1845 | "7015 0 44.20 403.35 1 0 \n", 1846 | "7016 0 73.35 931.55 0 1 \n", 1847 | "7017 0 64.10 4326.25 1 0 \n", 1848 | "7018 1 44.40 263.05 1 0 \n", 1849 | "7019 0 20.05 39.25 1 0 \n", 1850 | "7020 1 60.00 3316.10 0 1 \n", 1851 | "7021 1 75.75 75.75 0 1 \n", 1852 | "7022 0 69.50 2625.25 0 1 \n", 1853 | "7023 0 102.95 6886.25 1 0 \n", 1854 | "7024 0 78.70 1495.10 0 1 \n", 1855 | "7025 0 60.65 743.30 1 0 \n", 1856 | "7026 0 21.15 1419.40 1 0 \n", 1857 | "7027 0 84.80 1990.50 0 1 \n", 1858 | "7028 0 103.20 7362.90 1 0 \n", 1859 | "7029 0 29.60 346.45 1 0 \n", 1860 | "7030 1 74.40 306.60 0 1 \n", 1861 | "7031 0 105.65 6844.50 0 1 \n", 1862 | "\n", 1863 | " Partner_No Partner_Yes Dependents_No Dependents_Yes PhoneService_No \\\n", 1864 | "0 0 1 1 0 1 \n", 1865 | "1 1 0 1 0 0 \n", 1866 | "2 1 0 1 0 0 \n", 1867 | "3 1 0 1 0 1 \n", 1868 | "4 1 0 1 0 0 \n", 1869 | "5 1 0 1 0 0 \n", 1870 | "6 1 0 0 1 0 \n", 1871 | "7 1 0 1 0 1 \n", 1872 | "8 0 1 1 0 0 \n", 1873 | "9 1 0 0 1 0 \n", 1874 | "10 0 1 0 1 0 \n", 1875 | "11 1 0 1 0 0 \n", 1876 | "12 0 1 1 0 0 \n", 1877 | "13 1 0 1 0 0 \n", 1878 | "14 1 0 1 0 0 \n", 1879 | "15 0 1 0 1 0 \n", 1880 | "16 1 0 1 0 0 \n", 1881 | "17 1 0 0 1 0 \n", 1882 | "18 0 1 0 1 0 \n", 1883 | "19 1 0 1 0 0 \n", 1884 | "20 1 0 1 0 1 \n", 1885 | "21 0 1 1 0 0 \n", 1886 | "22 1 0 1 0 0 \n", 1887 | "23 0 1 1 0 0 \n", 1888 | "24 0 1 0 1 0 \n", 1889 | "25 1 0 1 0 0 \n", 1890 | "26 0 1 0 1 0 \n", 1891 | "27 0 1 0 1 1 \n", 1892 | "28 0 1 1 0 0 \n", 1893 | "29 1 0 0 1 0 \n", 1894 | "... ... ... ... ... ... \n", 1895 | "7002 1 0 1 0 0 \n", 1896 | "7003 1 0 1 0 0 \n", 1897 | "7004 0 1 1 0 0 \n", 1898 | "7005 1 0 1 0 0 \n", 1899 | "7006 1 0 1 0 0 \n", 1900 | "7007 0 1 0 1 0 \n", 1901 | "7008 1 0 1 0 0 \n", 1902 | "7009 0 1 0 1 0 \n", 1903 | "7010 1 0 1 0 0 \n", 1904 | "7011 1 0 1 0 0 \n", 1905 | "7012 0 1 1 0 0 \n", 1906 | "7013 0 1 1 0 0 \n", 1907 | "7014 1 0 1 0 0 \n", 1908 | "7015 1 0 1 0 0 \n", 1909 | "7016 1 0 1 0 0 \n", 1910 | "7017 0 1 1 0 0 \n", 1911 | "7018 1 0 1 0 1 \n", 1912 | "7019 1 0 1 0 0 \n", 1913 | "7020 0 1 1 0 0 \n", 1914 | "7021 1 0 1 0 0 \n", 1915 | "7022 1 0 1 0 0 \n", 1916 | "7023 1 0 1 0 0 \n", 1917 | "7024 1 0 1 0 0 \n", 1918 | "7025 1 0 1 0 1 \n", 1919 | "7026 1 0 1 0 0 \n", 1920 | "7027 0 1 0 1 0 \n", 1921 | "7028 0 1 0 1 0 \n", 1922 | "7029 0 1 0 1 1 \n", 1923 | "7030 0 1 1 0 0 \n", 1924 | "7031 1 0 1 0 0 \n", 1925 | "\n", 1926 | " ... PaymentMethod_Bank transfer (automatic) \\\n", 1927 | "0 ... 0 \n", 1928 | "1 ... 0 \n", 1929 | "2 ... 0 \n", 1930 | "3 ... 1 \n", 1931 | "4 ... 0 \n", 1932 | "5 ... 0 \n", 1933 | "6 ... 0 \n", 1934 | "7 ... 0 \n", 1935 | "8 ... 0 \n", 1936 | "9 ... 1 \n", 1937 | "10 ... 0 \n", 1938 | "11 ... 0 \n", 1939 | "12 ... 0 \n", 1940 | "13 ... 1 \n", 1941 | "14 ... 0 \n", 1942 | "15 ... 0 \n", 1943 | "16 ... 0 \n", 1944 | "17 ... 1 \n", 1945 | "18 ... 0 \n", 1946 | "19 ... 0 \n", 1947 | "20 ... 0 \n", 1948 | "21 ... 1 \n", 1949 | "22 ... 0 \n", 1950 | "23 ... 0 \n", 1951 | "24 ... 0 \n", 1952 | "25 ... 1 \n", 1953 | "26 ... 0 \n", 1954 | "27 ... 0 \n", 1955 | "28 ... 0 \n", 1956 | "29 ... 0 \n", 1957 | "... ... ... \n", 1958 | "7002 ... 1 \n", 1959 | "7003 ... 0 \n", 1960 | "7004 ... 0 \n", 1961 | "7005 ... 0 \n", 1962 | "7006 ... 1 \n", 1963 | "7007 ... 0 \n", 1964 | "7008 ... 0 \n", 1965 | "7009 ... 0 \n", 1966 | "7010 ... 0 \n", 1967 | "7011 ... 0 \n", 1968 | "7012 ... 0 \n", 1969 | "7013 ... 0 \n", 1970 | "7014 ... 1 \n", 1971 | "7015 ... 1 \n", 1972 | "7016 ... 0 \n", 1973 | "7017 ... 1 \n", 1974 | "7018 ... 0 \n", 1975 | "7019 ... 0 \n", 1976 | "7020 ... 0 \n", 1977 | "7021 ... 0 \n", 1978 | "7022 ... 0 \n", 1979 | "7023 ... 0 \n", 1980 | "7024 ... 1 \n", 1981 | "7025 ... 0 \n", 1982 | "7026 ... 1 \n", 1983 | "7027 ... 0 \n", 1984 | "7028 ... 0 \n", 1985 | "7029 ... 0 \n", 1986 | "7030 ... 0 \n", 1987 | "7031 ... 1 \n", 1988 | "\n", 1989 | " PaymentMethod_Credit card (automatic) PaymentMethod_Electronic check \\\n", 1990 | "0 0 1 \n", 1991 | "1 0 0 \n", 1992 | "2 0 0 \n", 1993 | "3 0 0 \n", 1994 | "4 0 1 \n", 1995 | "5 0 1 \n", 1996 | "6 1 0 \n", 1997 | "7 0 0 \n", 1998 | "8 0 1 \n", 1999 | "9 0 0 \n", 2000 | "10 0 0 \n", 2001 | "11 1 0 \n", 2002 | "12 1 0 \n", 2003 | "13 0 0 \n", 2004 | "14 0 1 \n", 2005 | "15 1 0 \n", 2006 | "16 0 0 \n", 2007 | "17 0 0 \n", 2008 | "18 1 0 \n", 2009 | "19 0 1 \n", 2010 | "20 0 1 \n", 2011 | "21 0 0 \n", 2012 | "22 0 0 \n", 2013 | "23 1 0 \n", 2014 | "24 1 0 \n", 2015 | "25 0 0 \n", 2016 | "26 0 1 \n", 2017 | "27 0 1 \n", 2018 | "28 1 0 \n", 2019 | "29 0 0 \n", 2020 | "... ... ... \n", 2021 | "7002 0 0 \n", 2022 | "7003 0 1 \n", 2023 | "7004 1 0 \n", 2024 | "7005 0 1 \n", 2025 | "7006 0 0 \n", 2026 | "7007 0 0 \n", 2027 | "7008 0 0 \n", 2028 | "7009 0 1 \n", 2029 | "7010 0 1 \n", 2030 | "7011 0 1 \n", 2031 | "7012 0 1 \n", 2032 | "7013 1 0 \n", 2033 | "7014 0 0 \n", 2034 | "7015 0 0 \n", 2035 | "7016 0 0 \n", 2036 | "7017 0 0 \n", 2037 | "7018 0 1 \n", 2038 | "7019 0 0 \n", 2039 | "7020 1 0 \n", 2040 | "7021 0 1 \n", 2041 | "7022 1 0 \n", 2042 | "7023 1 0 \n", 2043 | "7024 0 0 \n", 2044 | "7025 0 1 \n", 2045 | "7026 0 0 \n", 2046 | "7027 0 0 \n", 2047 | "7028 1 0 \n", 2048 | "7029 0 1 \n", 2049 | "7030 0 0 \n", 2050 | "7031 0 0 \n", 2051 | "\n", 2052 | " PaymentMethod_Mailed check tenure_group_1 - 12 tenure_group_13 - 24 \\\n", 2053 | "0 0 1 0 \n", 2054 | "1 1 0 0 \n", 2055 | "2 1 1 0 \n", 2056 | "3 0 0 0 \n", 2057 | "4 0 1 0 \n", 2058 | "5 0 1 0 \n", 2059 | "6 0 0 1 \n", 2060 | "7 1 1 0 \n", 2061 | "8 0 0 0 \n", 2062 | "9 0 0 0 \n", 2063 | "10 1 0 1 \n", 2064 | "11 0 0 1 \n", 2065 | "12 0 0 0 \n", 2066 | "13 0 0 0 \n", 2067 | "14 0 0 0 \n", 2068 | "15 0 0 0 \n", 2069 | "16 1 0 0 \n", 2070 | "17 0 0 0 \n", 2071 | "18 0 1 0 \n", 2072 | "19 0 0 1 \n", 2073 | "20 0 1 0 \n", 2074 | "21 0 1 0 \n", 2075 | "22 1 1 0 \n", 2076 | "23 0 0 0 \n", 2077 | "24 0 0 0 \n", 2078 | "25 0 0 0 \n", 2079 | "26 0 0 0 \n", 2080 | "27 0 1 0 \n", 2081 | "28 0 0 0 \n", 2082 | "29 1 0 1 \n", 2083 | "... ... ... ... \n", 2084 | "7002 0 0 0 \n", 2085 | "7003 0 0 0 \n", 2086 | "7004 0 0 0 \n", 2087 | "7005 0 1 0 \n", 2088 | "7006 0 0 0 \n", 2089 | "7007 1 1 0 \n", 2090 | "7008 1 0 0 \n", 2091 | "7009 0 1 0 \n", 2092 | "7010 0 1 0 \n", 2093 | "7011 0 0 0 \n", 2094 | "7012 0 0 0 \n", 2095 | "7013 0 0 0 \n", 2096 | "7014 0 0 1 \n", 2097 | "7015 0 1 0 \n", 2098 | "7016 1 0 1 \n", 2099 | "7017 0 0 0 \n", 2100 | "7018 0 1 0 \n", 2101 | "7019 1 1 0 \n", 2102 | "7020 0 0 0 \n", 2103 | "7021 0 1 0 \n", 2104 | "7022 0 0 0 \n", 2105 | "7023 0 0 0 \n", 2106 | "7024 0 0 1 \n", 2107 | "7025 0 1 0 \n", 2108 | "7026 0 0 0 \n", 2109 | "7027 1 0 1 \n", 2110 | "7028 0 0 0 \n", 2111 | "7029 0 1 0 \n", 2112 | "7030 1 1 0 \n", 2113 | "7031 0 0 0 \n", 2114 | "\n", 2115 | " tenure_group_25 - 36 tenure_group_37 - 48 tenure_group_49 - 60 \\\n", 2116 | "0 0 0 0 \n", 2117 | "1 1 0 0 \n", 2118 | "2 0 0 0 \n", 2119 | "3 0 1 0 \n", 2120 | "4 0 0 0 \n", 2121 | "5 0 0 0 \n", 2122 | "6 0 0 0 \n", 2123 | "7 0 0 0 \n", 2124 | "8 1 0 0 \n", 2125 | "9 0 0 0 \n", 2126 | "10 0 0 0 \n", 2127 | "11 0 0 0 \n", 2128 | "12 0 0 1 \n", 2129 | "13 0 0 1 \n", 2130 | "14 1 0 0 \n", 2131 | "15 0 0 0 \n", 2132 | "16 0 0 1 \n", 2133 | "17 0 0 0 \n", 2134 | "18 0 0 0 \n", 2135 | "19 0 0 0 \n", 2136 | "20 0 0 0 \n", 2137 | "21 0 0 0 \n", 2138 | "22 0 0 0 \n", 2139 | "23 0 0 1 \n", 2140 | "24 0 0 1 \n", 2141 | "25 1 0 0 \n", 2142 | "26 0 1 0 \n", 2143 | "27 0 0 0 \n", 2144 | "28 0 0 0 \n", 2145 | "29 0 0 0 \n", 2146 | "... ... ... ... \n", 2147 | "7002 0 1 0 \n", 2148 | "7003 0 1 0 \n", 2149 | "7004 1 0 0 \n", 2150 | "7005 0 0 0 \n", 2151 | "7006 0 0 1 \n", 2152 | "7007 0 0 0 \n", 2153 | "7008 0 1 0 \n", 2154 | "7009 0 0 0 \n", 2155 | "7010 0 0 0 \n", 2156 | "7011 0 0 0 \n", 2157 | "7012 0 0 0 \n", 2158 | "7013 0 1 0 \n", 2159 | "7014 0 0 0 \n", 2160 | "7015 0 0 0 \n", 2161 | "7016 0 0 0 \n", 2162 | "7017 0 0 0 \n", 2163 | "7018 0 0 0 \n", 2164 | "7019 0 0 0 \n", 2165 | "7020 0 0 1 \n", 2166 | "7021 0 0 0 \n", 2167 | "7022 0 1 0 \n", 2168 | "7023 0 0 0 \n", 2169 | "7024 0 0 0 \n", 2170 | "7025 0 0 0 \n", 2171 | "7026 0 0 0 \n", 2172 | "7027 0 0 0 \n", 2173 | "7028 0 0 0 \n", 2174 | "7029 0 0 0 \n", 2175 | "7030 0 0 0 \n", 2176 | "7031 0 0 0 \n", 2177 | "\n", 2178 | " tenure_group_61 - 72 \n", 2179 | "0 0 \n", 2180 | "1 0 \n", 2181 | "2 0 \n", 2182 | "3 0 \n", 2183 | "4 0 \n", 2184 | "5 0 \n", 2185 | "6 0 \n", 2186 | "7 0 \n", 2187 | "8 0 \n", 2188 | "9 1 \n", 2189 | "10 0 \n", 2190 | "11 0 \n", 2191 | "12 0 \n", 2192 | "13 0 \n", 2193 | "14 0 \n", 2194 | "15 1 \n", 2195 | "16 0 \n", 2196 | "17 1 \n", 2197 | "18 0 \n", 2198 | "19 0 \n", 2199 | "20 0 \n", 2200 | "21 0 \n", 2201 | "22 0 \n", 2202 | "23 0 \n", 2203 | "24 0 \n", 2204 | "25 0 \n", 2205 | "26 0 \n", 2206 | "27 0 \n", 2207 | "28 1 \n", 2208 | "29 0 \n", 2209 | "... ... \n", 2210 | "7002 0 \n", 2211 | "7003 0 \n", 2212 | "7004 0 \n", 2213 | "7005 0 \n", 2214 | "7006 0 \n", 2215 | "7007 0 \n", 2216 | "7008 0 \n", 2217 | "7009 0 \n", 2218 | "7010 0 \n", 2219 | "7011 1 \n", 2220 | "7012 1 \n", 2221 | "7013 0 \n", 2222 | "7014 0 \n", 2223 | "7015 0 \n", 2224 | "7016 0 \n", 2225 | "7017 1 \n", 2226 | "7018 0 \n", 2227 | "7019 0 \n", 2228 | "7020 0 \n", 2229 | "7021 0 \n", 2230 | "7022 0 \n", 2231 | "7023 1 \n", 2232 | "7024 0 \n", 2233 | "7025 0 \n", 2234 | "7026 1 \n", 2235 | "7027 0 \n", 2236 | "7028 1 \n", 2237 | "7029 0 \n", 2238 | "7030 0 \n", 2239 | "7031 1 \n", 2240 | "\n", 2241 | "[7032 rows x 50 columns]" 2242 | ] 2243 | }, 2244 | "execution_count": 4, 2245 | "metadata": {}, 2246 | "output_type": "execute_result" 2247 | } 2248 | ], 2249 | "source": [ 2250 | "x=df.drop('Churn',axis=1)\n", 2251 | "x" 2252 | ] 2253 | }, 2254 | { 2255 | "cell_type": "code", 2256 | "execution_count": 5, 2257 | "metadata": {}, 2258 | "outputs": [ 2259 | { 2260 | "data": { 2261 | "text/plain": [ 2262 | "0 0\n", 2263 | "1 0\n", 2264 | "2 1\n", 2265 | "3 0\n", 2266 | "4 1\n", 2267 | "5 1\n", 2268 | "6 0\n", 2269 | "7 0\n", 2270 | "8 1\n", 2271 | "9 0\n", 2272 | "10 0\n", 2273 | "11 0\n", 2274 | "12 0\n", 2275 | "13 1\n", 2276 | "14 0\n", 2277 | "15 0\n", 2278 | "16 0\n", 2279 | "17 0\n", 2280 | "18 1\n", 2281 | "19 0\n", 2282 | "20 1\n", 2283 | "21 0\n", 2284 | "22 1\n", 2285 | "23 0\n", 2286 | "24 0\n", 2287 | "25 0\n", 2288 | "26 1\n", 2289 | "27 1\n", 2290 | "28 0\n", 2291 | "29 1\n", 2292 | " ..\n", 2293 | "7002 0\n", 2294 | "7003 0\n", 2295 | "7004 0\n", 2296 | "7005 0\n", 2297 | "7006 0\n", 2298 | "7007 1\n", 2299 | "7008 0\n", 2300 | "7009 0\n", 2301 | "7010 1\n", 2302 | "7011 0\n", 2303 | "7012 0\n", 2304 | "7013 0\n", 2305 | "7014 0\n", 2306 | "7015 1\n", 2307 | "7016 0\n", 2308 | "7017 0\n", 2309 | "7018 0\n", 2310 | "7019 0\n", 2311 | "7020 0\n", 2312 | "7021 1\n", 2313 | "7022 0\n", 2314 | "7023 1\n", 2315 | "7024 0\n", 2316 | "7025 0\n", 2317 | "7026 0\n", 2318 | "7027 0\n", 2319 | "7028 0\n", 2320 | "7029 0\n", 2321 | "7030 1\n", 2322 | "7031 0\n", 2323 | "Name: Churn, Length: 7032, dtype: int64" 2324 | ] 2325 | }, 2326 | "execution_count": 5, 2327 | "metadata": {}, 2328 | "output_type": "execute_result" 2329 | } 2330 | ], 2331 | "source": [ 2332 | "y=df['Churn']\n", 2333 | "y" 2334 | ] 2335 | }, 2336 | { 2337 | "cell_type": "markdown", 2338 | "metadata": {}, 2339 | "source": [ 2340 | "##### Train Test Split" 2341 | ] 2342 | }, 2343 | { 2344 | "cell_type": "code", 2345 | "execution_count": 6, 2346 | "metadata": {}, 2347 | "outputs": [], 2348 | "source": [ 2349 | "x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2)" 2350 | ] 2351 | }, 2352 | { 2353 | "cell_type": "markdown", 2354 | "metadata": {}, 2355 | "source": [ 2356 | "#### Decision Tree Classifier" 2357 | ] 2358 | }, 2359 | { 2360 | "cell_type": "code", 2361 | "execution_count": 7, 2362 | "metadata": {}, 2363 | "outputs": [], 2364 | "source": [ 2365 | "model_dt=DecisionTreeClassifier(criterion = \"gini\",random_state = 100,max_depth=6, min_samples_leaf=8)" 2366 | ] 2367 | }, 2368 | { 2369 | "cell_type": "code", 2370 | "execution_count": 8, 2371 | "metadata": {}, 2372 | "outputs": [ 2373 | { 2374 | "data": { 2375 | "text/plain": [ 2376 | "DecisionTreeClassifier(max_depth=6, min_samples_leaf=8, random_state=100)" 2377 | ] 2378 | }, 2379 | "execution_count": 8, 2380 | "metadata": {}, 2381 | "output_type": "execute_result" 2382 | } 2383 | ], 2384 | "source": [ 2385 | "model_dt.fit(x_train,y_train)" 2386 | ] 2387 | }, 2388 | { 2389 | "cell_type": "code", 2390 | "execution_count": 9, 2391 | "metadata": {}, 2392 | "outputs": [ 2393 | { 2394 | "data": { 2395 | "text/plain": [ 2396 | "array([0, 0, 1, ..., 0, 0, 0], dtype=int64)" 2397 | ] 2398 | }, 2399 | "execution_count": 9, 2400 | "metadata": {}, 2401 | "output_type": "execute_result" 2402 | } 2403 | ], 2404 | "source": [ 2405 | "y_pred=model_dt.predict(x_test)\n", 2406 | "y_pred" 2407 | ] 2408 | }, 2409 | { 2410 | "cell_type": "code", 2411 | "execution_count": 10, 2412 | "metadata": {}, 2413 | "outputs": [ 2414 | { 2415 | "data": { 2416 | "text/plain": [ 2417 | "0.7818052594171997" 2418 | ] 2419 | }, 2420 | "execution_count": 10, 2421 | "metadata": {}, 2422 | "output_type": "execute_result" 2423 | } 2424 | ], 2425 | "source": [ 2426 | "model_dt.score(x_test,y_test)" 2427 | ] 2428 | }, 2429 | { 2430 | "cell_type": "code", 2431 | "execution_count": 11, 2432 | "metadata": {}, 2433 | "outputs": [ 2434 | { 2435 | "name": "stdout", 2436 | "output_type": "stream", 2437 | "text": [ 2438 | " precision recall f1-score support\n", 2439 | "\n", 2440 | " 0 0.82 0.89 0.86 1023\n", 2441 | " 1 0.63 0.49 0.55 384\n", 2442 | "\n", 2443 | " accuracy 0.78 1407\n", 2444 | " macro avg 0.73 0.69 0.70 1407\n", 2445 | "weighted avg 0.77 0.78 0.77 1407\n", 2446 | "\n" 2447 | ] 2448 | } 2449 | ], 2450 | "source": [ 2451 | "print(classification_report(y_test, y_pred, labels=[0,1]))" 2452 | ] 2453 | }, 2454 | { 2455 | "cell_type": "markdown", 2456 | "metadata": {}, 2457 | "source": [ 2458 | "###### As you can see that the accuracy is quite low, and as it's an imbalanced dataset, we shouldn't consider Accuracy as our metrics to measure the model, as Accuracy is cursed in imbalanced datasets.\n", 2459 | "\n", 2460 | "###### Hence, we need to check recall, precision & f1 score for the minority class, and it's quite evident that the precision, recall & f1 score is too low for Class 1, i.e. churned customers.\n", 2461 | "\n", 2462 | "###### Hence, moving ahead to call SMOTEENN (UpSampling + ENN)" 2463 | ] 2464 | }, 2465 | { 2466 | "cell_type": "code", 2467 | "execution_count": 12, 2468 | "metadata": {}, 2469 | "outputs": [], 2470 | "source": [ 2471 | "sm = SMOTEENN()\n", 2472 | "X_resampled, y_resampled = sm.fit_sample(x,y)" 2473 | ] 2474 | }, 2475 | { 2476 | "cell_type": "code", 2477 | "execution_count": 13, 2478 | "metadata": {}, 2479 | "outputs": [], 2480 | "source": [ 2481 | "xr_train,xr_test,yr_train,yr_test=train_test_split(X_resampled, y_resampled,test_size=0.2)" 2482 | ] 2483 | }, 2484 | { 2485 | "cell_type": "code", 2486 | "execution_count": 14, 2487 | "metadata": {}, 2488 | "outputs": [], 2489 | "source": [ 2490 | "model_dt_smote=DecisionTreeClassifier(criterion = \"gini\",random_state = 100,max_depth=6, min_samples_leaf=8)" 2491 | ] 2492 | }, 2493 | { 2494 | "cell_type": "code", 2495 | "execution_count": 15, 2496 | "metadata": {}, 2497 | "outputs": [ 2498 | { 2499 | "name": "stdout", 2500 | "output_type": "stream", 2501 | "text": [ 2502 | "0.934412265758092\n", 2503 | " precision recall f1-score support\n", 2504 | "\n", 2505 | " 0 0.97 0.88 0.93 540\n", 2506 | " 1 0.91 0.98 0.94 634\n", 2507 | "\n", 2508 | " accuracy 0.93 1174\n", 2509 | " macro avg 0.94 0.93 0.93 1174\n", 2510 | "weighted avg 0.94 0.93 0.93 1174\n", 2511 | "\n" 2512 | ] 2513 | } 2514 | ], 2515 | "source": [ 2516 | "model_dt_smote.fit(xr_train,yr_train)\n", 2517 | "yr_predict = model_dt_smote.predict(xr_test)\n", 2518 | "model_score_r = model_dt_smote.score(xr_test, yr_test)\n", 2519 | "print(model_score_r)\n", 2520 | "print(metrics.classification_report(yr_test, yr_predict))" 2521 | ] 2522 | }, 2523 | { 2524 | "cell_type": "code", 2525 | "execution_count": 16, 2526 | "metadata": {}, 2527 | "outputs": [ 2528 | { 2529 | "name": "stdout", 2530 | "output_type": "stream", 2531 | "text": [ 2532 | "[[477 63]\n", 2533 | " [ 14 620]]\n" 2534 | ] 2535 | } 2536 | ], 2537 | "source": [ 2538 | "print(metrics.confusion_matrix(yr_test, yr_predict))" 2539 | ] 2540 | }, 2541 | { 2542 | "cell_type": "markdown", 2543 | "metadata": {}, 2544 | "source": [ 2545 | "###### Now we can see quite better results, i.e. Accuracy: 92 %, and a very good recall, precision & f1 score for minority class.\n", 2546 | "\n", 2547 | "###### Let's try with some other classifier." 2548 | ] 2549 | }, 2550 | { 2551 | "cell_type": "markdown", 2552 | "metadata": {}, 2553 | "source": [ 2554 | "#### Random Forest Classifier" 2555 | ] 2556 | }, 2557 | { 2558 | "cell_type": "code", 2559 | "execution_count": 17, 2560 | "metadata": {}, 2561 | "outputs": [], 2562 | "source": [ 2563 | "from sklearn.ensemble import RandomForestClassifier" 2564 | ] 2565 | }, 2566 | { 2567 | "cell_type": "code", 2568 | "execution_count": 18, 2569 | "metadata": {}, 2570 | "outputs": [], 2571 | "source": [ 2572 | "model_rf=RandomForestClassifier(n_estimators=100, criterion='gini', random_state = 100,max_depth=6, min_samples_leaf=8)" 2573 | ] 2574 | }, 2575 | { 2576 | "cell_type": "code", 2577 | "execution_count": 19, 2578 | "metadata": {}, 2579 | "outputs": [ 2580 | { 2581 | "data": { 2582 | "text/plain": [ 2583 | "RandomForestClassifier(max_depth=6, min_samples_leaf=8, random_state=100)" 2584 | ] 2585 | }, 2586 | "execution_count": 19, 2587 | "metadata": {}, 2588 | "output_type": "execute_result" 2589 | } 2590 | ], 2591 | "source": [ 2592 | "model_rf.fit(x_train,y_train)" 2593 | ] 2594 | }, 2595 | { 2596 | "cell_type": "code", 2597 | "execution_count": 20, 2598 | "metadata": {}, 2599 | "outputs": [], 2600 | "source": [ 2601 | "y_pred=model_rf.predict(x_test)" 2602 | ] 2603 | }, 2604 | { 2605 | "cell_type": "code", 2606 | "execution_count": 21, 2607 | "metadata": {}, 2608 | "outputs": [ 2609 | { 2610 | "data": { 2611 | "text/plain": [ 2612 | "0.7953091684434968" 2613 | ] 2614 | }, 2615 | "execution_count": 21, 2616 | "metadata": {}, 2617 | "output_type": "execute_result" 2618 | } 2619 | ], 2620 | "source": [ 2621 | "model_rf.score(x_test,y_test)" 2622 | ] 2623 | }, 2624 | { 2625 | "cell_type": "code", 2626 | "execution_count": 22, 2627 | "metadata": {}, 2628 | "outputs": [ 2629 | { 2630 | "name": "stdout", 2631 | "output_type": "stream", 2632 | "text": [ 2633 | " precision recall f1-score support\n", 2634 | "\n", 2635 | " 0 0.82 0.92 0.87 1023\n", 2636 | " 1 0.69 0.45 0.55 384\n", 2637 | "\n", 2638 | " accuracy 0.80 1407\n", 2639 | " macro avg 0.75 0.69 0.71 1407\n", 2640 | "weighted avg 0.78 0.80 0.78 1407\n", 2641 | "\n" 2642 | ] 2643 | } 2644 | ], 2645 | "source": [ 2646 | "print(classification_report(y_test, y_pred, labels=[0,1]))" 2647 | ] 2648 | }, 2649 | { 2650 | "cell_type": "code", 2651 | "execution_count": 23, 2652 | "metadata": {}, 2653 | "outputs": [], 2654 | "source": [ 2655 | "sm = SMOTEENN()\n", 2656 | "X_resampled1, y_resampled1 = sm.fit_sample(x,y)" 2657 | ] 2658 | }, 2659 | { 2660 | "cell_type": "code", 2661 | "execution_count": 24, 2662 | "metadata": {}, 2663 | "outputs": [], 2664 | "source": [ 2665 | "xr_train1,xr_test1,yr_train1,yr_test1=train_test_split(X_resampled1, y_resampled1,test_size=0.2)" 2666 | ] 2667 | }, 2668 | { 2669 | "cell_type": "code", 2670 | "execution_count": 25, 2671 | "metadata": {}, 2672 | "outputs": [], 2673 | "source": [ 2674 | "model_rf_smote=RandomForestClassifier(n_estimators=100, criterion='gini', random_state = 100,max_depth=6, min_samples_leaf=8)" 2675 | ] 2676 | }, 2677 | { 2678 | "cell_type": "code", 2679 | "execution_count": 26, 2680 | "metadata": {}, 2681 | "outputs": [ 2682 | { 2683 | "data": { 2684 | "text/plain": [ 2685 | "RandomForestClassifier(max_depth=6, min_samples_leaf=8, random_state=100)" 2686 | ] 2687 | }, 2688 | "execution_count": 26, 2689 | "metadata": {}, 2690 | "output_type": "execute_result" 2691 | } 2692 | ], 2693 | "source": [ 2694 | "model_rf_smote.fit(xr_train1,yr_train1)" 2695 | ] 2696 | }, 2697 | { 2698 | "cell_type": "code", 2699 | "execution_count": 27, 2700 | "metadata": {}, 2701 | "outputs": [], 2702 | "source": [ 2703 | "yr_predict1 = model_rf_smote.predict(xr_test1)" 2704 | ] 2705 | }, 2706 | { 2707 | "cell_type": "code", 2708 | "execution_count": 28, 2709 | "metadata": {}, 2710 | "outputs": [], 2711 | "source": [ 2712 | "model_score_r1 = model_rf_smote.score(xr_test1, yr_test1)" 2713 | ] 2714 | }, 2715 | { 2716 | "cell_type": "code", 2717 | "execution_count": 29, 2718 | "metadata": {}, 2719 | "outputs": [ 2720 | { 2721 | "name": "stdout", 2722 | "output_type": "stream", 2723 | "text": [ 2724 | "0.9427350427350427\n", 2725 | " precision recall f1-score support\n", 2726 | "\n", 2727 | " 0 0.95 0.92 0.93 518\n", 2728 | " 1 0.94 0.96 0.95 652\n", 2729 | "\n", 2730 | " accuracy 0.94 1170\n", 2731 | " macro avg 0.94 0.94 0.94 1170\n", 2732 | "weighted avg 0.94 0.94 0.94 1170\n", 2733 | "\n" 2734 | ] 2735 | } 2736 | ], 2737 | "source": [ 2738 | "print(model_score_r1)\n", 2739 | "print(metrics.classification_report(yr_test1, yr_predict1))" 2740 | ] 2741 | }, 2742 | { 2743 | "cell_type": "code", 2744 | "execution_count": 30, 2745 | "metadata": {}, 2746 | "outputs": [ 2747 | { 2748 | "name": "stdout", 2749 | "output_type": "stream", 2750 | "text": [ 2751 | "[[478 40]\n", 2752 | " [ 27 625]]\n" 2753 | ] 2754 | } 2755 | ], 2756 | "source": [ 2757 | "print(metrics.confusion_matrix(yr_test1, yr_predict1))" 2758 | ] 2759 | }, 2760 | { 2761 | "cell_type": "markdown", 2762 | "metadata": {}, 2763 | "source": [ 2764 | "###### With RF Classifier, also we are able to get quite good results, infact better than Decision Tree.\n", 2765 | "\n", 2766 | "###### We can now further go ahead and create multiple classifiers to see how the model performance is, but that's not covered here, so you can do it by yourself :)" 2767 | ] 2768 | }, 2769 | { 2770 | "cell_type": "markdown", 2771 | "metadata": {}, 2772 | "source": [ 2773 | "#### Performing PCA" 2774 | ] 2775 | }, 2776 | { 2777 | "cell_type": "code", 2778 | "execution_count": 31, 2779 | "metadata": {}, 2780 | "outputs": [], 2781 | "source": [ 2782 | "# Applying PCA\n", 2783 | "from sklearn.decomposition import PCA\n", 2784 | "pca = PCA(0.9)\n", 2785 | "xr_train_pca = pca.fit_transform(xr_train1)\n", 2786 | "xr_test_pca = pca.transform(xr_test1)\n", 2787 | "explained_variance = pca.explained_variance_ratio_" 2788 | ] 2789 | }, 2790 | { 2791 | "cell_type": "code", 2792 | "execution_count": 32, 2793 | "metadata": {}, 2794 | "outputs": [], 2795 | "source": [ 2796 | "model=RandomForestClassifier(n_estimators=100, criterion='gini', random_state = 100,max_depth=6, min_samples_leaf=8)" 2797 | ] 2798 | }, 2799 | { 2800 | "cell_type": "code", 2801 | "execution_count": 33, 2802 | "metadata": {}, 2803 | "outputs": [ 2804 | { 2805 | "data": { 2806 | "text/plain": [ 2807 | "RandomForestClassifier(max_depth=6, min_samples_leaf=8, random_state=100)" 2808 | ] 2809 | }, 2810 | "execution_count": 33, 2811 | "metadata": {}, 2812 | "output_type": "execute_result" 2813 | } 2814 | ], 2815 | "source": [ 2816 | "model.fit(xr_train_pca,yr_train1)" 2817 | ] 2818 | }, 2819 | { 2820 | "cell_type": "code", 2821 | "execution_count": 34, 2822 | "metadata": {}, 2823 | "outputs": [], 2824 | "source": [ 2825 | "yr_predict_pca = model.predict(xr_test_pca)" 2826 | ] 2827 | }, 2828 | { 2829 | "cell_type": "code", 2830 | "execution_count": 35, 2831 | "metadata": {}, 2832 | "outputs": [], 2833 | "source": [ 2834 | "model_score_r_pca = model.score(xr_test_pca, yr_test1)" 2835 | ] 2836 | }, 2837 | { 2838 | "cell_type": "code", 2839 | "execution_count": 36, 2840 | "metadata": {}, 2841 | "outputs": [ 2842 | { 2843 | "name": "stdout", 2844 | "output_type": "stream", 2845 | "text": [ 2846 | "0.7239316239316239\n", 2847 | " precision recall f1-score support\n", 2848 | "\n", 2849 | " 0 0.72 0.61 0.66 518\n", 2850 | " 1 0.72 0.81 0.77 652\n", 2851 | "\n", 2852 | " accuracy 0.72 1170\n", 2853 | " macro avg 0.72 0.71 0.71 1170\n", 2854 | "weighted avg 0.72 0.72 0.72 1170\n", 2855 | "\n" 2856 | ] 2857 | } 2858 | ], 2859 | "source": [ 2860 | "print(model_score_r_pca)\n", 2861 | "print(metrics.classification_report(yr_test1, yr_predict_pca))" 2862 | ] 2863 | }, 2864 | { 2865 | "cell_type": "markdown", 2866 | "metadata": {}, 2867 | "source": [ 2868 | "##### With PCA, we couldn't see any better results, hence let's finalise the model which was created by RF Classifier, and save the model so that we can use it in a later stage :)" 2869 | ] 2870 | }, 2871 | { 2872 | "cell_type": "markdown", 2873 | "metadata": {}, 2874 | "source": [ 2875 | "#### Pickling the model" 2876 | ] 2877 | }, 2878 | { 2879 | "cell_type": "code", 2880 | "execution_count": 37, 2881 | "metadata": {}, 2882 | "outputs": [], 2883 | "source": [ 2884 | "import pickle" 2885 | ] 2886 | }, 2887 | { 2888 | "cell_type": "code", 2889 | "execution_count": 38, 2890 | "metadata": {}, 2891 | "outputs": [], 2892 | "source": [ 2893 | "filename = 'model.sav'" 2894 | ] 2895 | }, 2896 | { 2897 | "cell_type": "code", 2898 | "execution_count": 39, 2899 | "metadata": {}, 2900 | "outputs": [], 2901 | "source": [ 2902 | "pickle.dump(model_rf_smote, open(filename, 'wb'))" 2903 | ] 2904 | }, 2905 | { 2906 | "cell_type": "code", 2907 | "execution_count": 40, 2908 | "metadata": {}, 2909 | "outputs": [], 2910 | "source": [ 2911 | "load_model = pickle.load(open(filename, 'rb'))" 2912 | ] 2913 | }, 2914 | { 2915 | "cell_type": "code", 2916 | "execution_count": 41, 2917 | "metadata": {}, 2918 | "outputs": [], 2919 | "source": [ 2920 | "model_score_r1 = load_model.score(xr_test1, yr_test1)" 2921 | ] 2922 | }, 2923 | { 2924 | "cell_type": "code", 2925 | "execution_count": 42, 2926 | "metadata": {}, 2927 | "outputs": [ 2928 | { 2929 | "data": { 2930 | "text/plain": [ 2931 | "0.9427350427350427" 2932 | ] 2933 | }, 2934 | "execution_count": 42, 2935 | "metadata": {}, 2936 | "output_type": "execute_result" 2937 | } 2938 | ], 2939 | "source": [ 2940 | "model_score_r1" 2941 | ] 2942 | }, 2943 | { 2944 | "cell_type": "markdown", 2945 | "metadata": {}, 2946 | "source": [ 2947 | "##### Our final model i.e. RF Classifier with SMOTEENN, is now ready and dumped in model.sav, which we will use and prepare API's so that we can access our model from UI." 2948 | ] 2949 | } 2950 | ], 2951 | "metadata": { 2952 | "kernelspec": { 2953 | "display_name": "Python 3", 2954 | "language": "python", 2955 | "name": "python3" 2956 | }, 2957 | "language_info": { 2958 | "codemirror_mode": { 2959 | "name": "ipython", 2960 | "version": 3 2961 | }, 2962 | "file_extension": ".py", 2963 | "mimetype": "text/x-python", 2964 | "name": "python", 2965 | "nbconvert_exporter": "python", 2966 | "pygments_lexer": "ipython3", 2967 | "version": "3.7.3" 2968 | } 2969 | }, 2970 | "nbformat": 4, 2971 | "nbformat_minor": 2 2972 | } 2973 | --------------------------------------------------------------------------------