data_preprocessing.py

# -*- coding: utf-8 -*-
"""Data Preprocessing.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1n4DDN-lgGvEAHp-oyICct_VkkrzFaR31
"""

#importing libraries
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

#loading my dataset
df=pd.read_csv('/content/covid19_global_statistics_2026.csv')
df.head()

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

#Handling missing values
for col in ['population', 'new_cases', 'active_cases', 'cases_per_million', 'new_deaths', 'deaths_per_million', 'total_deaths', 'tests_per_million', 'total_tests']:
    if df[col].isnull().any():
        df[col] = df[col].fillna(df[col].median())

if df['continent'].isnull().any():
    df['continent'] = df['continent'].fillna(df['continent'].mode()[0])

df['date'] = pd.to_datetime(df['date'])

df.isnull().sum()

#Making histogram
plt.hist(df['new_cases'],bins=20,color='purple',label='New Cases')
plt.hist(df['active_cases'],bins=20,color='pink', label='Active Cases')
plt.legend()
plt.title('Distribution of New Cases and Active Cases')
plt.xlabel('Count')
plt.ylabel('Frequency')
plt.show()

#Heatmap of the data
sns.heatmap(df.corr(numeric_only=True),annot=True)
plt.show

#One Hot encoding
df=pd.get_dummies(df,drop_first=True)
df.head()

#Training the model
X=df.drop(['total_deaths', 'date'],axis=1)
y=df['total_deaths']
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2,random_state=42)
scaler=StandardScaler()
X_train_scaled=scaler.fit_transform(X_train)