cordon-thiago

cordon-thiago

cordon-thiago

hardbounce_2[['emailDomain_cat', 'emailDomainPiece1', 'emailDomainPiece2', 'regDate_n', 'birthDate_n'
             ,'monthsSinceRegDate', 'age', 'percNumbersInEmailUser', 'hasNumberInEmailUser', 'emailUserCharQty'
             ,'flgHardBounce_n']].to_csv('datasets/hardbounce_featureEngineering.csv', sep=';',index=False)

cordon-thiago

# Import libraries
import pandas as pd
import numpy as np
from functions import aux_functions

# Calculate character qty in e-mail user
hardbounce_2['emailUserCharQty'] = hardbounce_2['email'].apply(lambda x : len(aux_functions.getEmailUser(x)))

cordon-thiago

# Import libraries
import pandas as pd
import numpy as np
import seaborn as sns
from functions import aux_functions

# Extract e-mail domain
hardbounce_2['emailDomain'] = hardbounce_2['email'].apply(aux_functions.getEmailDomain)

# count by domain

cordon-thiago

import matplotlib.pyplot as plt

def plot_roc_curve(fpr, tpr, label=None):
    """
    The ROC curve, modified from
    Hands-On Machine learning with Scikit-Learn and TensorFlow; p.91

    tpr = true positive rate
    fpr = false positive rate
    """

cordon-thiago

import pandas as pd
import numpy as np  
from datetime import date
from functions import aux_functions

curr_date = pd.to_datetime(date.today())

hardbounce_2['age'] = (curr_date - hardbounce_2['birthDate_n']) / np.timedelta64(1, 'Y')

# There are ages missing

cordon-thiago

import pandas as pd
import numpy as np
from datetime import date
from functions import aux_functions

curr_date = pd.to_datetime(date.today())

hardbounce_2['monthsSinceRegDate'] = (curr_date - hardbounce_2['regDate_n']) / np.timedelta64(1, 'M')

# There are rows with monthsSinceRegDate missing

cordon-thiago

import pandas as pd

hardbounce_2['flgHardBounce_n'] = hardbounce_2.flgHardBounce.astype(int)
hardbounce_2['regDate_n'] = pd.to_datetime(hardbounce_2['regDate'])
hardbounce_2['birthDate_n'] = pd.to_datetime(hardbounce_2['birthDate'], errors = 'coerce')

cordon-thiago

# Import libraries
import pandas as pd
import numpy as np
from functions import aux_functions

hardbounce = pd.read_csv('datasets/hardbounce_sample.csv',sep=';')

# Run the function on dataset
aux_functions.percMissing(hardbounce)