1

# Import libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
# Load dataset
df = pd.read_csv(r"E:\Kiran\DSI\ML and NN\Lab\Program 1\archive\diabetes.csv")
# Display first 5 records
print("First 5 Records")
print(df.head())
# Check missing values (0 indicates missing)
print("\nMissing Values Before Preprocessing")
# Columns where 0 represents missing values
missing_cols = ['Glucose', 'BloodPressure', 'SkinThickness', 'Insulin', 'BMI']
print(df[missing_cols].eq(0).sum())
# Replace 0 with NaN and fill missing values with median
for col in missing_cols:
 df[col] = df[col].replace(0, np.nan)
 df[col] = df[col].fillna(df[col].median())
# Check missing values after preprocessing
print("\nMissing Values After Preprocessing")
print(df.isnull().sum())
# Summary statistics
print("\nSummary Statistics")
print(df.describe())
# Normalize numerical columns using Min-Max Normalization
num_cols = ['Pregnancies', 'Glucose', 'BloodPressure',
 'SkinThickness', 'Insulin', 'BMI',
 'DiabetesPedigreeFunction', 'Age']
df[num_cols] = (df[num_cols] - df[num_cols].min()) / (df[num_cols].max() -
df[num_cols].min())
print("\nFirst 5 Records After Normalization")
print(df.head())
# -------------------- Visualizations --------------------
# 1. Histogram
df.hist(figsize=(10, 8))
plt.suptitle("Histogram of Features")
plt.show()
# 2. Diabetes Outcome Bar Chart
df['Outcome'].value_counts().plot(kind='bar')
plt.title("Diabetes Outcome")
plt.xlabel("Outcome")
plt.ylabel("Count")
plt.xticks([0, 1], ['No Diabetes', 'Diabetes'], rotation=0)
plt.show()
# 3. Correlation Matrix
plt.figure(figsize=(8, 6))
plt.imshow(df.corr(), cmap='coolwarm', interpolation='nearest')
plt.colorbar()
plt.xticks(range(len(df.columns)), df.columns, rotation=90)
plt.yticks(range(len(df.columns)), df.columns)
plt.title("Correlation Matrix")
plt.show()