from sklearn.model_selection import GridSearchCV, RandomizedSearchCV
from sklearn.ensemble import RandomForestClassifier

grid_search = GridSearchCV(
    estimator=RandomForestClassifier(random_state=42, n_jobs=-1),
    param_grid={

from sklearn.compose import ColumnTransformer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.ensemble import RandomForestClassifier

from sklearn.cluster import KMeans, DBSCAN, AgglomerativeClustering
from sklearn.metrics import silhouette_score
from sklearn.preprocessing import StandardScaler

X_scaled = StandardScaler().fit_transform(X)

from sklearn.linear_model import LinearRegression, Ridge, Lasso, ElasticNet
from sklearn.metrics import mean_absolute_error, root_mean_squared_error

models = {
    'linear': LinearRegression(),
    'ridge': Ridge(alpha=1.0),

from sklearn.ensemble import RandomForestClassifier, HistGradientBoostingClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import roc_auc_score
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer

from sklearn.model_selection import StratifiedKFold, train_test_split, cross_validate
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler
from sklearn.linear_model import LogisticRegression

standard_pipeline = Pipeline([
    ('scaler', StandardScaler()),

import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler

import pandas as pd

orders = pd.read_parquet('orders.parquet')
orders['ordered_at'] = pd.to_datetime(orders['ordered_at'])

reference_date = orders['ordered_at'].max() + pd.Timedelta(days=1)

import pandas as pd

df = pd.read_parquet('churn_training.parquet')

print('shape:', df.shape)
print('target balance:', df['churned'].value_counts(normalize=True).round(3))

import pandas as pd
import plotly.express as px

df = pd.read_csv('marketing_performance.csv')
fig = px.scatter(
    df,

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

train_df = pd.read_parquet('train_features.parquet')
prod_df = pd.read_parquet('production_features.parquet')