demo.py

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

df = pd.read_csv('task1/healthcare-dataset-stroke-data.csv')
# Display the first few rows of the dataset
print(df.head())
# Display basic information about the dataset
print(df.info())
# Display basic statistics of the dataset
print(df.describe())

# Check for missing values
print("Missing values in each column:")
print(df.isnull().sum())

#check for skewness in 'bmi' column
print("Mean:", df['bmi'].mean())
print("Median:", df['bmi'].median())
print("Skewness:", df['bmi'].skew())
sns.histplot(df['bmi'], kde=True)
plt.title('Distribution of BMI')
plt.show()

# Drop the 'id' column as it is not useful for analysis
df = df.drop('id', axis=1)


# Fill missing values in 'bmi' with the median (because the data is skewed)
df['bmi'] = df['bmi'].fillna(df['bmi'].median())

# Check for missing values again
print("Missing values after filling 'bmi':")
print(df.isnull().sum())  # done 

print(df.select_dtypes(include='object').columns)

# Convert categorical variables to numerical using one-hot encoding
df = pd.get_dummies(df, columns=['gender', 'ever_married', 'work_type', 'Residence_type', 'smoking_status'], drop_first=True, dtype=int)

# Display the first few rows after encoding
print(df.head())

from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()

# # Fit and transform selected columns
df[['age', 'avg_glucose_level', 'bmi']] = scaler.fit_transform(df[['age', 'avg_glucose_level', 'bmi']])
# Display the first few rows after scaling
print(df.head())

import matplotlib.pyplot as plt
import seaborn as sns

numerical_cols = ['age', 'avg_glucose_level', 'bmi']

plt.figure(figsize=(15, 4))
for i, col in enumerate(numerical_cols, 1):
    plt.subplot(1, 3, i)
    sns.boxplot(data=df, y=col)
    plt.title(f'Boxplot of {col}')
plt.tight_layout()
plt.show()

def remove_outliers(df, column):
    Q1 = df[column].quantile(0.25)
    Q3 = df[column].quantile(0.75)
    IQR = Q3 - Q1
    lower_bound = Q1 - 1.5 * IQR
    upper_bound = Q3 + 1.5 * IQR
    return df[(df[column] >= lower_bound) & (df[column] <= upper_bound)]

# Remove outliers from each column
for col in numerical_cols:
    df = remove_outliers(df, col)
numerical_cols = ['age', 'avg_glucose_level', 'bmi']

# Plot boxplots after removing outliers

plt.figure(figsize=(15, 4))
for i, col in enumerate(numerical_cols, 1):
    plt.subplot(1, 3, i)
    sns.boxplot(data=df, y=col)
    plt.title(f'Boxplot of {col}')

plt.tight_layout()
plt.show()

df.to_csv('task1/cleaned_stroke_data.csv', index=False)