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

data = pd.read_csv ('U.S._Chronic_Disease_Indicators__CDI_.csv')

data

asthma = pd.read_csv('asthma.csv') asthma.head()

#looking specifically at asthma mortality rate: asthma_mortality = asthma[asthma["Question"] == "Asthma mortality rate"]

#pivot table by both location(state) and year cleaned_asthma = asthma_mortality.pivot_table(index=["LocationDesc", "YearStart"], columns="DataValueType", values = "DataValue")

cleaned_asthma

#Clean the pivot table by dropping United States cleaned_asthma = cleaned_asthma.drop('United States') #Reset index cleaned_asthma.reset_index(level=0, inplace=True) cleaned_asthma.reset_index(level=0, inplace=True)

cleaned_asthma

#Visualize the average mortality rate of asthma from 2010-2017 across states average = cleaned_asthma.groupby('LocationDesc', as_index=False)['Number'].mean() plt.figure(figsize=(15,8)) sns.barplot(x='LocationDesc', y='Number', data=average) plt.xticks(rotation=90); plt.xlabel('States') plt.ylabel('Average Mortality Rate 2010-2017') plt.title('Average Mortality Rate of Asthma 2010-2017 Across States')

state_fips = pd.read_csv('us-state-ansi-fips.csv') cleaned_state_fips = state_fips[['stname', ' st']] cleaned_state_fips.head()

#importing the pm2 data pm2 = pd.read_csv("pm2.csv") pm2.head()

#importing the oz data file oz = pd.read_csv("oz.csv")

oz.head()

#data cleaning oz_cleaned = oz[['statefips', 'ds_o3_pred']]

#data cleaning pm2_cleaned = pm2[['statefips', 'ds_pm_pred']] pm2_cleaned.head()

average_pm_by_statefips = pm2_cleaned.groupby(by = 'statefips').mean() average_pm_by_statefips.head()

plt.hist(average_pm_by_statefips['ds_pm_pred'], bins = 20) plt.title("average PM2.5 concentration in μg/m3 2011-2014") plt.xlabel('PM2.5 concentration in μg/m3') plt.ylabel('number of states')

average_pm_by_statefips['statefips'] = average_pm_by_statefips.index average_pm_by_statefips = average_pm_by_statefips.sort_values(by = 'ds_pm_pred', ascending = False) average_pm_by_statefips = average_pm_by_statefips.rename(columns={"statefips": "state_fips"}) average_pm_by_statefips.head()

average_pm_by_statename = average_pm_by_statefips.merge(cleaned_state_fips, left_on='state_fips', right_on=' st') average_pm_by_statename

average_pm_for_all = average_pm_by_statename['ds_pm_pred'].mean() average_pm_for_all

plt.figure(figsize=(15,8)) graph = sns.barplot(x='stname', y='ds_pm_pred', data=average_pm_by_statename) graph.axhline(average_pm_for_all) plt.xticks(rotation=90); plt.xlabel('States') plt.ylabel('Average PM2.5 2011-2014') plt.title('Average PM2.5 concentration in μg/m3 2011-2014 Across States')

average_oz_by_statefips = oz_cleaned.groupby(by = 'statefips').mean() average_oz_by_statefips.head()

plt.hist(average_oz_by_statefips['ds_o3_pred'], bins = 20) plt.title("average OZ in ppb 2011-2014") plt.xlabel('OZ concentration in ppb') plt.ylabel('number of states')

average_oz_by_statefips['statefips'] = average_oz_by_statefips.index average_oz_by_statefips = average_oz_by_statefips.sort_values(by = 'ds_o3_pred', ascending = False) average_oz_by_statefips = average_oz_by_statefips.rename(columns={"statefips": "state_fips"}) average_oz_by_statefips.head()

average_oz_by_statename = average_oz_by_statefips.merge(cleaned_state_fips, left_on='state_fips', right_on=' st') average_oz_by_statename

average_oz_for_all = average_oz_by_statename['ds_o3_pred'].mean() average_oz_for_all

plt.figure(figsize=(15,8)) graph = sns.barplot(x='stname', y='ds_o3_pred', data=average_oz_by_statename) graph.axhline(average_oz_for_all) plt.xticks(rotation=90); plt.xlabel('States') plt.ylabel('Average OZ Concentration 2011-2014') plt.title('Average OZ concentration in ppb (parts per billion) 2011-2014 Across States')