7 ML

import pandas as pd

from sklearn.model_selection import train_test_split

from sklearn.preprocessing import StandardScaler

#task 1:

df = pd.read_csv("telecom_customer_churn.csv")

#task 2:

print(df.head())

print(df.info())

print(df.describe())

#task 3:

df.fillna(method='ffill', inplace=True)

#task 4:

df.drop_duplicates(inplace=True)

#task 5:

df['Gender'] = df['Gender'].str.lower()

#task 6:

df['TotalCharges'] = pd.to_numric(df['Total Charges'], errors='coerce')

#task 7:

z_scores = (df['TotalCharges'] - df['Total Charges'].mean())/df['Total Charges'].std()

df = df[(z_scores.abs() < 3)]

#task 8:

df['TenureinMonths'] =df['Tenure in Months']*30

#task 9:

scaler = StandardScaler()

df[['MonthlyCharge', 'TotalCharges', 'TenurenMonths']] = Scaler.fit_transform[['Monthly Charge', 'Total Charges', 'Tenure in Months']])

#task 10:

X = df.drop('Churn Category', axis=1)

y = df['Churn Category']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

#Task 11:

df.to_csv("Cleaned_telecom_customer_churn.", index=False)

Be Androidian