Duplicate and pipeline leakage

# Purpose: demonstrate Duplicate and pipeline leakage with a small, inspectable example.
# Follow the comments and printed stages to connect each operation with its result.
# Import the library or helper used in this example.
# Step 1 — Import the module so its functions/classes are available to the rest of this example.
import numpy as np
# Import the library or helper used in this example.
# Step 2 — Import the module so its functions/classes are available to the rest of this example.
import pandas as pd
# Import the library or helper used in this example.
# Step 3 — Import only the named objects needed by the following steps, keeping dependencies explicit.
from sklearn.compose import ColumnTransformer
# Import the library or helper used in this example.
# Step 4 — Import only the named objects needed by the following steps, keeping dependencies explicit.
from sklearn.impute import SimpleImputer
# Import the library or helper used in this example.
# Step 5 — Import only the named objects needed by the following steps, keeping dependencies explicit.
from sklearn.pipeline import Pipeline
# Import the library or helper used in this example.
# Step 6 — Import only the named objects needed by the following steps, keeping dependencies explicit.
from sklearn.preprocessing import OneHotEncoder, StandardScaler
# Import the library or helper used in this example.
# Step 7 — Import only the named objects needed by the following steps, keeping dependencies explicit.
from sklearn.linear_model import LogisticRegression

# Create a small labelled dataset that is easy to inspect by eye.
# Step 8 — Construct `X` as a tabular object with named columns for inspectable analysis.
X = pd.DataFrame({"age":[22,25,28,31,35,39,42,46,50,54,58,61],"income":[40,45,np.nan,50,55,60,62,68,72,76,80,85],"city":["A","A","B","B","A","C","C","A","B","C","A","B"]})
# Create the numerical values used in the calculation.
# Step 9 — Construct `y` as an array so vectorised numerical operations can be applied consistently.
y = np.array([0,0,0,0,0,1,0,1,1,1,1,1])
# Print this intermediate result so you can verify the workflow step by step.
# Step 10 — Display the current value explicitly so the result/state can be inspected during execution.
print("STEP 1 · Data shape:", X.shape)
# Store this intermediate value with a descriptive name for the next step.
# Step 11 — Create `num` as the scaling object; its parameters will be learned from training data.
num = Pipeline([("impute",SimpleImputer(strategy="median")),("scale",StandardScaler())])
# Step 12 — Compute the right-hand expression and store its result in `cat` for the next step.
cat = OneHotEncoder(handle_unknown="ignore")
# Step 13 — Compute the right-hand expression and store its result in `pre` for the next step.
pre = ColumnTransformer([("num",num,["age","income"]),("cat",cat,["city"])])
# Configure the estimator or pipeline with the chosen settings.
# Step 14 — Instantiate `model` with the chosen algorithm/configuration before fitting it to data.
model = Pipeline([("pre",pre),("clf",LogisticRegression(max_iter=500))])
# Fit only on the training data so the model learns from allowed information.
# Step 15 — Fit the model or transformer, learning its parameters from the supplied training data.
model.fit(X,y)
# Print this intermediate result so you can verify the workflow step by step.
# Step 16 — Display the current value explicitly so the result/state can be inspected during execution.
print("STEP 2 · Pipeline trained with steps:", list(model.named_steps))
# Print this intermediate result so you can verify the workflow step by step.
# Step 17 — Display the current value explicitly so the result/state can be inspected during execution.
print("STEP 3 · Training accuracy:", round(model.score(X,y),3))
# Generate class probabilities so confidence and thresholds can be inspected.
# Step 18 — Display the current value explicitly so the result/state can be inspected during execution.
print("STEP 3 · First probabilities:", model.predict_proba(X[:3])[:,1].round(3).tolist())