├── COVID-19_DATA SET.csv.zip ├── FINAL PROJECT.zip ├── Figure_1.png ├── Figure_2.png ├── Figure_3.png ├── Figure_4.png ├── README.md ├── Vaccination PPT.zip ├── index.py CODEzip.zip └── index.py saurav /COVID-19_DATA SET.csv.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sauravsinghsurya/covid-19-python-project/1bfacb9379ee287356d3ed115bb078098e8f6888/COVID-19_DATA SET.csv.zip -------------------------------------------------------------------------------- /FINAL PROJECT.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sauravsinghsurya/covid-19-python-project/1bfacb9379ee287356d3ed115bb078098e8f6888/FINAL PROJECT.zip -------------------------------------------------------------------------------- /Figure_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sauravsinghsurya/covid-19-python-project/1bfacb9379ee287356d3ed115bb078098e8f6888/Figure_1.png -------------------------------------------------------------------------------- /Figure_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sauravsinghsurya/covid-19-python-project/1bfacb9379ee287356d3ed115bb078098e8f6888/Figure_2.png -------------------------------------------------------------------------------- /Figure_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sauravsinghsurya/covid-19-python-project/1bfacb9379ee287356d3ed115bb078098e8f6888/Figure_3.png -------------------------------------------------------------------------------- /Figure_4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sauravsinghsurya/covid-19-python-project/1bfacb9379ee287356d3ed115bb078098e8f6888/Figure_4.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # covid-19-python-project -------------------------------------------------------------------------------- /Vaccination PPT.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sauravsinghsurya/covid-19-python-project/1bfacb9379ee287356d3ed115bb078098e8f6888/Vaccination PPT.zip -------------------------------------------------------------------------------- /index.py CODEzip.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Sauravsinghsurya/covid-19-python-project/1bfacb9379ee287356d3ed115bb078098e8f6888/index.py CODEzip.zip -------------------------------------------------------------------------------- /index.py saurav: -------------------------------------------------------------------------------- 1 | # Import libraries 2 | import pandas as pd 3 | import numpy as np 4 | import seaborn as sns 5 | import matplotlib.pyplot as plt 6 | 7 | # Load the dataset 8 | file_path = "Covid 19.csv" 9 | 10 | file_path ='/Users/sauravsurya/Desktop/Covid 19.csv' # <-- Update your path 11 | df = pd.read_csv(file_path) 12 | 13 | # Display first 10 rows 14 | print("First 10 rows of the dataset:") 15 | print(df.head(10)) 16 | 17 | # Display column names 18 | print("\nColumn names:") 19 | print(df.columns.tolist()) 20 | 21 | # Convert 'As of Date' to datetime 22 | df['Week End'] = pd.to_datetime(df['Week End'], errors='coerce') 23 | 24 | # ------------------------------- 25 | # New Objective: Calculate Risk Ratio 26 | # ------------------------------- 27 | 28 | # Step 1: Select important columns 29 | df_risk = df[['Age Group', 'Outcome', 'Unvaccinated Rate', 'Vaccinated Rate']].dropna() 30 | 31 | # Step 2: Calculate Risk Ratio 32 | df_risk['Risk Ratio (Unvaccinated/Vaccinated)'] = df_risk['Unvaccinated Rate'] / df_risk['Vaccinated Rate'] 33 | 34 | # Step 3: Average Risk Ratio by Age Group and Outcome 35 | risk_summary = df_risk.groupby(['Age Group', 'Outcome'])['Risk Ratio (Unvaccinated/Vaccinated)'].mean().reset_index() 36 | 37 | print("\nAverage Risk Ratio (Unvaccinated vs Vaccinated) by Age Group and Outcome:") 38 | print(risk_summary) 39 | 40 | # Step 4: Plot Risk Ratio 41 | plt.figure(figsize=(14, 7)) 42 | sns.barplot(data=risk_summary, x='Age Group', y='Risk Ratio (Unvaccinated/Vaccinated)', hue='Outcome', palette='coolwarm') 43 | plt.title('Risk of Unvaccinated vs Vaccinated by Age Group and Outcome') 44 | plt.ylabel('Risk Ratio (Higher means More Risk for Unvaccinated)') 45 | plt.xlabel('Age Group') 46 | plt.xticks(rotation=45) 47 | plt.grid(axis='y', linestyle='--', alpha=0.7) 48 | plt.legend(title='Outcome') 49 | plt.tight_layout() 50 | plt.show() 51 | 52 | # ------------------------------- 53 | # Other Previous Graphs 54 | # ------------------------------- 55 | 56 | # Filter deaths 57 | deaths_df = df[df['Outcome'] == 'Deaths'] 58 | 59 | # 1. Average Unvaccinated Death Rate 60 | average_unvaccinated_death_rate = np.nanmean(deaths_df['Unvaccinated Rate']) 61 | print(f"\nAverage Unvaccinated Death Rate: {average_unvaccinated_death_rate:.2f}") 62 | 63 | # 2. Bar Plot: Death Rate Comparison 64 | deaths_df_grouped = deaths_df.groupby('Age Group')[['Unvaccinated Rate', 'Vaccinated Rate']].mean().reset_index() 65 | deaths_df_melted = deaths_df_grouped.melt(id_vars='Age Group', value_vars=['Unvaccinated Rate', 'Vaccinated Rate'], 66 | var_name='Vaccination Status', value_name='Rate') 67 | 68 | plt.figure(figsize=(12, 6)) 69 | sns.barplot(data=deaths_df_melted, x='Age Group', y='Rate', hue='Vaccination Status') 70 | plt.title('Unvaccinated vs Vaccinated Death Rate by Age Group') 71 | plt.xticks(rotation=45) 72 | plt.ylabel('Death Rate') 73 | plt.xlabel('Age Group') 74 | plt.tight_layout() 75 | plt.show() 76 | 77 | # 3. Pie Chart: Total Outcomes 78 | unvaccinated_total = deaths_df['Outcome Unvaccinated'].sum() 79 | vaccinated_total = deaths_df['Outcome Vaccinated'].sum() 80 | 81 | plt.figure(figsize=(6, 6)) 82 | plt.pie( 83 | [unvaccinated_total, vaccinated_total], 84 | labels=['Unvaccinated', 'Vaccinated'], 85 | autopct='%1.1f%%', 86 | startangle=140, 87 | colors=['#ff9999', '#66b3ff'] 88 | ) 89 | plt.title('Overall Outcome Distribution (Deaths)') 90 | plt.axis('equal') 91 | plt.show() 92 | 93 | # 4. Histogram: Unvaccinated Death Rate Distribution 94 | plt.figure(figsize=(8, 5)) 95 | plt.hist(deaths_df['Unvaccinated Rate'].dropna(), bins=20, color='skyblue', edgecolor='black') 96 | plt.title('Distribution of Unvaccinated Death Rates') 97 | plt.xlabel('Unvaccinated Death Rate') 98 | plt.ylabel('Frequency') 99 | plt.grid(axis='y', linestyle='--', alpha=0.7) 100 | plt.show() 101 | 102 | # 5. Line Plot: Trend of Death Rates 103 | deaths_time_df = df[df['Outcome'] == 'Deaths'].sort_values('Week End') 104 | 105 | plt.figure(figsize=(14, 6)) 106 | sns.lineplot(data=deaths_time_df, x='Week End', y='Unvaccinated Rate', label='Unvaccinated Rate', color='red') 107 | sns.lineplot(data=deaths_time_df, x='Week End', y='Vaccinated Rate', label='Vaccinated Rate', color='green') 108 | plt.title('Trend of Death Rates Over Time') 109 | plt.xlabel('Date') 110 | plt.ylabel('Death Rate') 111 | plt.legend() 112 | plt.grid(True) 113 | plt.tight_layout() 114 | plt.show() 115 | 116 | # 6. Box Plot: Death Rate by Age Group 117 | plt.figure(figsize=(12, 6)) 118 | sns.boxplot(data=deaths_df, x='Age Group', y='Unvaccinated Rate') 119 | plt.title('Distribution of Unvaccinated Death Rates by Age Group') 120 | plt.xlabel('Age Group') 121 | plt.ylabel('Unvaccinated Death Rate') 122 | plt.grid(axis='y', linestyle='--', alpha=0.7) 123 | plt.tight_layout() 124 | plt.show() --------------------------------------------------------------------------------