from google.

colab import drive

drive.mount('/content/drive/')​

import pandas as pd

import numpy as np

# Assuming the file is in the 'My Drive' folder of your Google Drive

file_path = '/content/drive/My Drive/healthcare-dataset/train.csv'

df = pd.read_csv(file_pa)

​
Part 1: Data Preprocessing

import pandas as pd # Import pandas for data manipulation

data = pd.read_csv("Data.csv") # Load the dataset

data.head() # View first few rows of the dataset

data.isnull().sum() # Check for missing values

data.fillna(data.mean(), inplace=True) # Replace missing values with column mean

data.fillna(data.mean(), inplace=True) # Replaces NaN with column mean

data.fillna(data.median(), inplace=True) # Replaces NaN with column median

for column in data.columns:

data[column].fillna(data[column].mode()[0], inplace=True) # Fill NaN with the most frequent

data.fillna(0, inplace=True) # Replaces all NaN with 0 (or any chosen constant)

data.dropna(inplace=True) # Removes any rows with NaN values

data.dropna(axis=1, inplace=True) # Removes columns that have missing values

from sklearn.preprocessing import LabelEncoder # For converting categorical to numerical

le = LabelEncoder()

data["Gender"] = le.fit_transform(data["Gender"]) # Encode 'Gender' column

from sklearn.preprocessing import StandardScaler # For scaling numerical features

scaler = StandardScaler()

data[["Age", "Salary"]] = scaler.fit_transform(data[["Age", "Salary"]]) # Normalize 'Age' and 'Salary'

df2['age'].fillna(df2['age'].mean(),inplace = True)
df2['age'] #for age change in filna to cover null value to replace null​
Part 2: Data Visualization​
✅
​
1. Correlation Heatmap

import seaborn as sns

import matplotlib.pyplot as plt

sns.heatmap(data.corr(), annot=True, cmap="coolwarm") # Shows relationships between numerical

plt.title("Correlation Heatmap")

plt.show()

✅ 2. Pairplot
sns.pairplot(data, hue="Purchased") # Visualize pairwise relationships between features

✅ 3. Boxplot​
sns.boxplot(data=data[["Age", "Salary"]]) # Detect outliers and understand value distributions

✅ 4. Histogram
data["Age"].hist(bins=20)

plt.title("Distribution of Age")

plt.xlabel("Age")

plt.ylabel("Frequency")

plt.show()

✅ 5. Scatter Plot​
sns.scatterplot(x="Age", y="Salary", hue="Purchased", data=data)

plt.title("Age vs Salary")

plt.show()

✅ 6. Count Plot​
sns.countplot(x="Purchased", data=data) # Count of each class/category

✅ 7. Pie Chart (for categorical distribution)

plt.title("Gender Distribution")

plt.show()

✅ 8. Bar Plot
sns.barplot(x="Gender", y="Salary", data=data) # Compare average Salary by Gender

import seaborn as sns

sns.heatmap(data.corr(), annot=True) # Correlation heatmap

plt.title("Correlation Heatmap")

plt.show()

sns.pairplot(data) # Pairwise scatter plots for all numerical features

sns.scatterplot(x="Age", y="Salary", hue="Purchased", data=data) # Scatter plot for Age vs Salary

sns.boxplot(data=data[["Age", "Salary"]]) # Box plot to detect outliers and distributions

Part 3: Model Preparation

from sklearn.model_selection import train_test_split

X = data[["Age", "Salary"]] # Features

y = data["Purchased"] # Target

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # Split dataset

Model 1: Linear Regression

from sklearn.linear_model import LinearRegression

model = LinearRegression()

model.fit(X_train, y_train)

y_pred = model.predict(X_test)

from sklearn.metrics import mean_squared_error, r2_score

print("MSE:", mean_squared_error(y_test, y_pred))

print("R2 Score:", r2_score(y_test, y_pred))

Model 2: Logistic Regression

from sklearn.linear_model import LogisticRegression

model = LogisticRegression()

model.fit(X_train, y_train)

y_pred = model.predict(X_test)

from sklearn.metrics import accuracy_score, confusion_matrix

print("Accuracy:", accuracy_score(y_test, y_pred))

print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))

from sklearn.tree import DecisionTreeClassifier

model = DecisionTreeClassifier()

model.fit(X_train, y_train)

y_pred = model.predict(X_test)

print("Accuracy:", accuracy_score(y_test, y_pred))

print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))

Model 4: Random Forest

from sklearn.ensemble import RandomForestClassifier

model = RandomForestClassifier()

model.fit(X_train, y_train)

y_pred = model.predict(X_test)

print("Accuracy:", accuracy_score(y_test, y_pred))

print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))

Model 5: Support Vector Machine (SVM)

from sklearn.svm import SVC

model = SVC()

model.fit(X_train, y_train)

y_pred = model.predict(X_test)

print("Accuracy:", accuracy_score(y_test, y_pred))

print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))

Model 6: K-Nearest Neighbors (KNN)

from sklearn.neighbors import KNeighborsClassifier

model = KNeighborsClassifier(n_neighbors=3)

model.fit(X_train, y_train)

y_pred = model.predict(X_test)

print("Accuracy:", accuracy_score(y_test, y_pred))

print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))

from sklearn.naive_bayes import GaussianNB

model = GaussianNB()

model.fit(X_train, y_train)

y_pred = model.predict(X_test)

print("Accuracy:", accuracy_score(y_test, y_pred))

print("Confusion Matrix:\n", confusion_matrix(y_test, y_pred))