DATA SCIENCE PYTHON PLAYGROUND

Flexibility and explanation have different costs.

ColumnTransformer, LinearRegression, DecisionTreeRegressor and common-fold CV.

Revisit: Regression checkpoint

Compare both prepared candidates, tune tree depth, diagnose and nominate before final evaluation.

This complete script replaces the editor contents. It includes the input setup and the workflow.

import numpy as np
import pandas as pd
df=pd.read_csv('data/ml-learning/ML-X03.csv')
from sklearn.base import clone
from sklearn.model_selection import train_test_split, KFold, cross_validate, cross_val_predict, GridSearchCV
from sklearn.dummy import DummyRegressor
from sklearn.metrics import root_mean_squared_error

import matplotlib.pyplot as plt
import seaborn as sns
X=df[['sugarpercent', 'pricepercent', 'chocolate', 'fruity', 'caramel', 'peanutyalmondy', 'nougat', 'crispedricewafer', 'hard', 'bar', 'pluribus']]
y=df['winpercent']
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=.2,random_state=42)
folds=KFold(n_splits=5,shuffle=True,random_state=42)
candidates={}
grids={}
# Prepare inputs and construct the candidate pipeline.
preprocessor = 'passthrough'
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LinearRegression
model = LinearRegression()
pipeline = Pipeline([('prepare', preprocessor), ('model', model)])
model = pipeline
candidates['multiple_linear']=model
grids['multiple_linear']=None
# Prepare inputs and construct the candidate pipeline.
preprocessor = 'passthrough'
from sklearn.pipeline import Pipeline
from sklearn.tree import DecisionTreeRegressor
model = DecisionTreeRegressor(random_state=42)
pipeline = Pipeline([('prepare', preprocessor), ('model', model)])
model = pipeline
candidates['regression_tree']=model
grids['regression_tree']={'model__max_depth': [3, 5, None]}
# Validate initial candidates on matching training folds.
initial_results={name:cross_validate(candidate,X_train,y_train,cv=folds,scoring='neg_root_mean_squared_error') for name,candidate in candidates.items()}
# Compare with a simple reference before tuning.
reference_results=cross_validate(DummyRegressor(strategy='mean'),X_train,y_train,cv=folds,scoring='neg_root_mean_squared_error')
rows=[]
selected={}
for name,candidate in candidates.items():
    initial=initial_results[name]
    grid=grids[name]
    if grid:
        search=GridSearchCV(candidate,grid,cv=folds,scoring='neg_root_mean_squared_error',n_jobs=1)
        search.fit(X_train,y_train)
        selected[name]=search.best_estimator_
        validation_score=float(search.best_score_)
        settings=search.best_params_
    else:
        selected[name]=candidate
        validation_score=float(np.mean(initial['test_score']))
        settings='Keep defaults: no production search'
    rows.append({'model':name,'initial_score':float(np.mean(initial['test_score'])),'selected_score':validation_score,'settings':str(settings)})
cv_results=pd.DataFrame(rows).set_index('model')
# This solution nominates by mean training-fold score. Other evidence-based choices can be defensible.
chosen_name=cv_results.selected_score.idxmax()
chosen=selected[chosen_name]
oof_predictions=cross_val_predict(chosen,X_train,y_train,cv=folds)
diagnostic_y=y_train
residuals=pd.DataFrame({'actual':diagnostic_y,'predicted':oof_predictions,'residual':diagnostic_y-oof_predictions})
fig,ax=plt.subplots(figsize=(6,4))
sns.scatterplot(x=residuals.predicted,y=residuals.residual,s=12,ax=ax)
ax.axhline(0,color='black')
ax.set(xlabel='Training-validation prediction',ylabel='Residual',title='Training-only residuals')
fig.tight_layout()
fig.savefig('diagnostic.png',dpi=150,bbox_inches='tight')
final_model=clone(chosen).fit(X_train,y_train)
final_predictions=final_model.predict(X_test)
final_rmse=root_mean_squared_error(y_test,final_predictions)
print('Final RMSE:',final_rmse)

import numpy as np
import pandas as pd
df=pd.read_csv('data/ml-learning/ML-X03.csv')

Why these steps exist

• Numeric measurements and binary flags retain their declared meanings in both pipelines. Only the tree has a depth search here; common-fold evidence and OOF residuals support nomination before final RMSE. Coefficients and tree importance have different interpretations and neither establishes causality.

Another valid approach

Equivalent ordinary Python is welcome. A defensible candidate or grouping need not match the solution’s choice; objective evidence must remain consistent.