import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.impute import SimpleImputer
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import precision_score, recall_score, f1_score, confusion_matrix

# 1. LOAD DATASET

df = pd.read_csv("diabetes.csv")

print(df.head())
print("Missing Values:\n", df.isnull().sum())
print("Class Distribution:\n", df["Outcome"].value_counts())

# 2. EDA AND INVALID ZERO VALUES

zero_cols = ["Glucose", "BloodPressure", "SkinThickness", "Insulin", "BMI"]

print("\nInvalid Zero Counts:")
print((df[zero_cols] == 0).sum())

# Replace invalid zeros with NaN
df[zero_cols] = df[zero_cols].replace(0, np.nan)

print("\nMissing Values After Replacement:")
print(df.isnull().sum())

df.hist(figsize=(10, 8))
plt.suptitle("Feature Distributions")
plt.tight_layout()
plt.show()

# 3. FEATURES AND TARGET

df = df.dropna(subset=["Outcome"])

X = df.drop("Outcome", axis=1)
y = df["Outcome"]

print("Target: Outcome (0 = No Diabetes, 1 = Diabetes)")

# 4. TRAIN-TEST SPLIT

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)

# Handle missing values using training data
imputer = SimpleImputer(strategy="median")
X_train = imputer.fit_transform(X_train)
X_test = imputer.transform(X_test)

# Standardization
scaler = StandardScaler()

X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# 5. TRAIN KNN FOR DIFFERENT K VALUES

for k in [3, 5, 7]:

    model = KNeighborsClassifier(n_neighbors=k)
    model.fit(X_train, y_train)

    y_pred = model.predict(X_test)

    # 6. EVALUATE AND COMPARE

    print("\nK =", k)
    print("Precision:", precision_score(y_test, y_pred))
    print("Recall:", recall_score(y_test, y_pred))
    print("F1 Score:", f1_score(y_test, y_pred))
    print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))


# ENHANCED: Shape and imputed/scaled training summary; existing histograms retained
print("Dataset shape:", df.shape)
print("Scaled training-feature summary:\n", pd.DataFrame(X_train, columns=X.columns).describe())
