import warnings; warnings.filterwarnings("ignore")
import numpy as np
np.random.seed(42)
# This will suppress warnings to keep our notebook clean

# Data setup (Pima Indians Diabetes Dataset)
import pandas as pd
url = 'https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv'
cols = ['Pregnancies','Glucose','BloodPressure','SkinThickness','Insulin','BMI','DiabetesPedigree','Age','Outcome']
df = pd.read_csv(url, names=cols)
print(df.shape)
print(df.head(3))

# Checking for missing values
df.isnull().sum()

# Checking for strange zeros (as missing) in some columns
cols_with_zeros = ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI']
for col in cols_with_zeros:
    print(f"{col}:", (df[col] == 0).sum())
    

# Replacing zeros with NaN in suspicious columns
import numpy as np
for col in cols_with_zeros:
    df[col] = df[col].replace(0, np.nan)
df[cols_with_zeros].isnull().sum()

# Filling missing values with the column median
df.fillna(df.median(), inplace=True)

# Summary statistics
df.describe()

# Plot histograms for each feature
import matplotlib.pyplot as plt
df.hist(figsize=(10,7)); plt.tight_layout(); plt.show()

# Split the data into training and testing sets
from sklearn.model_selection import train_test_split
X = df.drop('Outcome', axis=1)
y = df['Outcome']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
print(X_train.shape, X_test.shape)

# Bagging Classifier with Decision Trees
from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier
bag = BaggingClassifier(DecisionTreeClassifier(), n_estimators=50, random_state=42)
bag.fit(X_train, y_train)
bag_score = bag.score(X_test, y_test)
print(f"Bagging Test Accuracy: {bag_score:.3f}")

# Compare: A single Decision Tree
tree = DecisionTreeClassifier(random_state=42)
tree.fit(X_train, y_train)
tree_score = tree.score(X_test, y_test)
print(f"Single Tree Test Accuracy: {tree_score:.3f}")

# Random Forest Classifier
from sklearn.ensemble import RandomForestClassifier
rf = RandomForestClassifier(n_estimators=100, random_state=42)
rf.fit(X_train, y_train)
rf_score = rf.score(X_test, y_test)
print(f"Random Forest Test Accuracy: {rf_score:.3f}")

# What features mattered most? Feature importance
importances = rf.feature_importances_
for col, imp in zip(X.columns, importances):
    print(f"{col}: {imp:.3f}")
    

# Visual confusion matrix for Random Forest
from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay
y_pred = rf.predict(X_test)
cm = confusion_matrix(y_test, y_pred)
disp = ConfusionMatrixDisplay(cm)
disp.plot(); plt.show()

# Interactive: Make your own diabetes prediction
data_point = []
for col in X.columns:
    value = input(f"Enter value for {col}: ")
    data_point.append(float(value))
prediction = rf.predict([data_point])[0]
result = 'Diabetes' if prediction == 1 else 'No Diabetes'
print(f"Prediction: {result}")

# Challenge: Bagging with more or fewer trees
for n in [10, 50, 200]:
    bag = BaggingClassifier(DecisionTreeClassifier(), n_estimators=n, random_state=42)
    bag.fit(X_train, y_train)
    bag_score = bag.score(X_test, y_test)
    print(f"Bagging with {n} trees, Test Accuracy: {bag_score:.3f}")
    

# Extra tip: Save and reload your Random Forest
import joblib
joblib.dump(rf, 'rf_model.joblib')
rf_new = joblib.load('rf_model.joblib')
print(f"Reloaded forest, Test Accuracy: {rf_new.score(X_test, y_test):.3f}")

# Practice: Try another classifier (optional)
from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier()
knn.fit(X_train, y_train)
knn_score = knn.score(X_test, y_test)
print(f"kNN Test Accuracy: {knn_score:.3f}")