codesnips
python 
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

Baseline classifiers in scikit-learn for fast benchmark setting

scikit-learn classification baselines
by Dr. Elena Vasquez 1 tab
python 
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

Train test split and stratified cross validation done properly

cross-validation evaluation scikit-learn
by Dr. Elena Vasquez 1 tab
python 
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler
from sklearn.linear_model import LogisticRegression

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

Scaling and normalization choices for different model families

feature-scaling normalization machine-learning
by Dr. Elena Vasquez 1 tab
python 
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

Encoding categorical variables without creating leakage

categorical-encoding preprocessing scikit-learn
by Dr. Elena Vasquez 1 tab
python 
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)

Feature engineering for recency, frequency, and monetary behavior

feature-engineering pandas rfm
by Dr. Elena Vasquez 1 tab
python 
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))

Exploratory data analysis checklist for tabular ML projects

eda machine-learning tabular-data
by Dr. Elena Vasquez 1 tab
python 
import pandas as pd
import plotly.express as px

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

Interactive Plotly figures for exploratory stakeholder reviews

plotly dashboards interactive-visualization
by Dr. Elena Vasquez 1 tab
python 
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')

Statistical visualizations for distribution and drift analysis

seaborn data-drift distributions
by Dr. Elena Vasquez 1 tab
python 
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({

Matplotlib and Seaborn defaults that make charts publication ready

matplotlib seaborn visualization
by Dr. Elena Vasquez 1 tab
python 
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],

Linear algebra patterns for similarity and projection tasks

numpy linear-algebra embeddings
by Dr. Elena Vasquez 1 tab
python 
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],

NumPy broadcasting for vectorized feature engineering

numpy broadcasting vectorization
by Dr. Elena Vasquez 1 tab
python 
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()

Time series resampling and rolling windows in pandas

pandas time-series resampling
by Dr. Elena Vasquez 1 tab