Dr. Elena Vasquez

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')

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

sns.set_theme(style='whitegrid', palette='deep', context='talk')
plt.rcParams.update({

import numpy as np

embeddings = np.array([
    [0.9, 0.1, 0.2],
    [0.1, 0.8, 0.3],
    [0.7, 0.2, 0.4],

import numpy as np

features = np.array([
    [120.0, 3.0, 10.0],
    [90.0, 5.0, 7.0],
    [150.0, 2.0, 14.0],

import pandas as pd

df = pd.read_csv('traffic.csv', parse_dates=['timestamp'])
df['timestamp'] = pd.to_datetime(df['timestamp'], utc=True)
df = df.set_index('timestamp').sort_index()

import pandas as pd

customers = pd.read_parquet('customers.parquet')
orders = pd.read_parquet('orders.parquet')

assert customers['customer_id'].is_unique, 'customer table must be unique by customer_id'

import pandas as pd

df = pd.read_parquet('events.parquet')
df['event_date'] = pd.to_datetime(df['event_date'])
df['month'] = df['event_date'].dt.to_period('M').astype(str)

import pandas as pd

df = pd.read_csv('customers.csv')

df.columns = df.columns.str.strip().str.lower().str.replace(' ', '_', regex=False)