import pandas as pd
df = pd.read_csv("data/ml-ready/cdi-customer-churn.csv")
df.head()| customer_id | tenure_months | monthly_spend | support_calls | contract_type | autopay | churn | |
|---|---|---|---|---|---|---|---|
| 0 | C100000 | 6 | 45.85 | 2 | one-year | no | 0 |
| 1 | C100001 | 17 | 69.95 | 1 | month-to-month | yes | 1 |
| 2 | C100002 | 64 | 70.98 | 0 | month-to-month | no | 1 |
| 3 | C100003 | 59 | 33.02 | 2 | month-to-month | yes | 0 |
| 4 | C100004 | 8 | 70.74 | 0 | month-to-month | yes | 1 |
X = df.drop(columns="churn")
y = df["churn"]from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.2, random_state=42, stratify=y
)numeric_features = X.select_dtypes(include=["int64", "float64"]).columns
categorical_features = X.select_dtypes(include=["object"]).columns
numeric_features, categorical_features(Index(['tenure_months', 'monthly_spend', 'support_calls'], dtype='str'),
Index(['customer_id', 'contract_type', 'autopay'], dtype='str'))from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.pipeline import Pipeline
numeric_transformer = Pipeline(
steps=[("scaler", StandardScaler())]
)
categorical_transformer = Pipeline(
steps=[("encoder", OneHotEncoder(handle_unknown="ignore"))]
)
preprocessor = ColumnTransformer(
transformers=[
("num", numeric_transformer, numeric_features),
("cat", categorical_transformer, categorical_features)
]
)