Capstone: A scikit-learn Tour & Building a Real Predictive Model

from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression, Ridge
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
import numpy as np

X = df_cars[["mileage", "year"]]
y = df_cars["price"]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)  # ml1-2

scaler = StandardScaler()
X_train_s = scaler.fit_transform(X_train)
X_test_s = scaler.transform(X_test)

model = Ridge(alpha=1.0)   # ml1-3's own LinearRegression, ml1-8's own L2 regularization applied
model.fit(X_train_s, y_train)

preds = model.predict(X_test_s)
mae = mean_absolute_error(y_test, preds)              # ml1-4
rmse = np.sqrt(mean_squared_error(y_test, preds))      # ml1-4
r2 = r2_score(y_test, preds)                           # ml1-4

cv_scores = cross_val_score(model, X_train_s, y_train, cv=5)   # ml1-8

This is ml1-3's own coefficients and ml1-4's own metrics, now wrapped in ml1-8's own regularization and cross-validation — the full arc this course built one deliberate piece at a time.

from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix, precision_score, recall_score, f1_score

X = pd.get_dummies(df_emp[["department", "age", "years_at_company", "salary"]])
y = df_emp["left_company"].map({"Yes": 1, "No": 0})

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)  # ml1-2
X_train_s = scaler.fit_transform(X_train)
X_test_s = scaler.transform(X_test)

logit = LogisticRegression()          # ml1-5
logit.fit(X_train_s, y_train)

forest = RandomForestClassifier(n_estimators=200, random_state=42)   # ml1-7
forest.fit(X_train, y_train)          # trees don't require scaling — a real, honest asymmetry worth noting

for name, preds in [("Logistic", logit.predict(X_test_s)), ("Forest", forest.predict(X_test))]:
    print(name, precision_score(y_test, preds), recall_score(y_test, preds), f1_score(y_test, preds))  # ml1-6

forest.feature_importances_   # does the forest agree with ml1-5's own salary finding?