mortalitymosaiclcdtn.py

# -*- coding: utf-8 -*-
"""MortalityMosaicLCDTN.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1FLReFlU3L5ILTBN11Hw3pf8IaeqeDJOD
"""

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error

from google.colab import drive
drive.mount('/content/drive')

import google.colab

!pip install drive

file_path = '/content/drive/MyDrive/dscproject/LCD_TN.csv'
LCD_TN = pd.read_csv(file_path)

# Separate the DataFrame by each year
LCD_2019 = LCD_TN[LCD_TN['year'] == 2019]
LCD_2020 = LCD_TN[LCD_TN['year'] == 2020]
LCD_2021 = LCD_TN[LCD_TN['year'] == 2021]

import seaborn as sns

# Comparative Analysis of Leading Causes of Death
plt.figure(figsize=(12, 6))
sns.barplot(data= LCD_2019, x='COUNTY', y='NUMBER', hue='CAUSE')
plt.title('Comparative Analysis of Leading Causes of Death between Counties')
plt.xlabel('County')
plt.ylabel('Number of Deaths')
plt.xticks(rotation=45)
plt.legend(title='Cause', bbox_to_anchor=(1.05, 1), loc='upper left')
plt.tight_layout()
plt.show()

# Comparative Analysis of Leading Causes of Death
plt.figure(figsize=(12, 6))
sns.barplot(data= LCD_2020, x='COUNTY', y='NUMBER', hue='CAUSE')
plt.title('Comparative Analysis of Leading Causes of Death between Counties')
plt.xlabel('County')
plt.ylabel('Number of Deaths')
plt.xticks(rotation=45)
plt.legend(title='Cause', bbox_to_anchor=(1.05, 1), loc='upper left')
plt.tight_layout()
plt.show()

# Comparative Analysis of Leading Causes of Death
plt.figure(figsize=(12, 6))
sns.barplot(data=LCD_2021, x='COUNTY', y='NUMBER', hue='CAUSE')
plt.title('Comparative Analysis of Leading Causes of Death between Counties')
plt.xlabel('County')
plt.ylabel('Number of Deaths')
plt.xticks(rotation=45)
plt.legend(title='Cause', bbox_to_anchor=(1.05, 1), loc='upper left')
plt.tight_layout()
plt.show()