Starter Project

#import necessary packages import pandas as pd import matplotlib.pyplot as plt import scipy.stats as stats from scipy.stats import pearsonr from functools import partial import numpy as np from scipy.optimize import curve_fit import seaborn as sns

#import data electiondf = pd.read_csv("npr-2016-election-data.csv") confirmed = pd.read_csv("covid_confirmed_usafacts (1).csv") county = pd.read_csv('covid_county_population_usafacts.csv') #merge data -- question 3 df = pd.DataFrame.merge(county,confirmed) df.head() df = pd.DataFrame.merge(df, electiondf)

by_state_df = df.groupby( 'State' ).sum() by_state_df = by_state_df.iloc[:,2:] by_state_df.head() by_state_df['Total Cases'] = by_state_df.iloc[:,:-2] by_state_df['Total Cases'] #

#curve fitting # quesiton 4 b0 = [] b1 = [] b2 = [] #logistic model def logistic_curve (x,β0,β1,β2): return β0 / (1+np.exp(β1*(-x+β2))) ''' b0 - guess cases so far b1 - 1 b2 - len data/ 2 ''' #function takes a state abbreviation as input and returns the series of cases as output def cases_over_time_in_state ( state_abbreviation ): cases_in_state = by_state_df.loc[state_abbreviation, 'Total Cases'] for index, r, in by_state_df.iterrows(): xs = np.arrange(len(r)) ys = r guess_betas = [ys.max(), 1, len(df)/2] found_betas, covariance = curve_fit(logistic_curve,xs, ys,p0=guess_betas) β0,β1,β2 = found_betas b0.append(β0) b1.append(β1) b2.append(β2) model = lambda x: logistic_curve(x,β0,β1,β2) plt.scatter(xs, ys) plt.plot(xs, model(xs), color= "red") plt.show() #df['b0']=pd.Series(b0) #df['b1']=pd.Series(b1) #df['b2']=pd.Series(b2) by_state_df['b0']=pd.Series(b0) by_state_df['b1']=pd.Series(b1) by_state_df['b2']=pd.Series(b2) print(by_state_df.head())

       stateFIPS  1/22/20  1/23/20  1/24/20  1/25/20  1/26/20  1/27/20  \
State                                                                    
AK            62        0        0        0        0        0        0   
AL            68        0        0        0        0        0        0   
AR           380        0        0        0        0        0        0   
AZ            64        0        0        0        0        1        1   
CA           360        0        0        0        0        2        3   

       1/28/20  1/29/20  1/30/20  ...  10/10/20  10/11/20  10/12/20  10/13/20  \
State                             ...                                           
AK           0        0        0  ...      9430      9686      9877     10028   
AL           0        0        0  ...    164525    165342    166076    167193   
AR           0        0        0  ...     92220     92833     93487     94167   
AZ           1        1        1  ...    224970    225575    226050    226734   
CA           3        4        4  ...    852159    854377    857638    862113   

       Clinton  Trump  Total Cases  b0  b1  b2  
State                                           
AK        1178   1643           62 NaN NaN NaN  
AL        2380   4284           68 NaN NaN NaN  
AR        2584   4560          380 NaN NaN NaN  
AZ         720    800           64 NaN NaN NaN  
CA        3720   1980          360 NaN NaN NaN  

[5 rows x 273 columns]
/opt/venv/lib/python3.7/site-packages/ipykernel_launcher.py:38: DeprecationWarning: The default dtype for empty Series will be 'object' instead of 'float64' in a future version. Specify a dtype explicitly to silence this warning.
/opt/venv/lib/python3.7/site-packages/ipykernel_launcher.py:39: DeprecationWarning: The default dtype for empty Series will be 'object' instead of 'float64' in a future version. Specify a dtype explicitly to silence this warning.
/opt/venv/lib/python3.7/site-packages/ipykernel_launcher.py:40: DeprecationWarning: The default dtype for empty Series will be 'object' instead of 'float64' in a future version. Specify a dtype explicitly to silence this warning.

#question 5 correlation = df.corr() print(correlation)

#subset candidates Clinton = df['Clinton'] Trump = df['Trump'] #define variables for correlation analysis ########################################### #most recent number of cases recent_total_cases = df['Total Cases'] #projected maximum number of cases max_cases = df[b0] #most recent number of cases per capita per_capcases = recent_total_cases/df['population'] #projected maximum number of cases per capita max_percap = max_cases/df['population'] #time of maximum increase timemax = df['b2'] * 2 #rate of increase roi = df['b1']/timemax #evaluate correlations ######################### # most recent number of cases corr_recent_total_cases_clinton, _ = pearsonr(Clinton, recent_total_cases) corr_recent_total_cases_trump, _ = pearsonr(Trump, recent_total_cases) print(corr_recent_total_cases_clinton) print(corr_recent_total_cases_trump) # most recent number of cases per capita corr_per_capcases_clinton, _ = pearsonr(Clinton, per_capcases) corr_per_capcases_trump, _ = pearsonr(Trump, per_capcases) print(corr_maxpercap_clinton) print(corr_maxpercap_trump) # projected maximum number of cases corr_max_cases_clinton, _ = pearsonr(Clinton, max_cases) corr_max_cases_trump, _ = pearsonr(Trump, max_cases) print(corr_max_cases_clinton) print(corr_max_cases_trump) # projected maximum number of cases per capita corr_max_percap_clinton, _ = pearsonr(Clinton, max_percap) corr_max_percap_trump,_ = pearsonr(Trump, max_percap) print(corr_max_percap_clinton) print(corr_max_percap_trump) # rate of increase corr_increase_clinton, _ = pearsonr(Clinton, roi) corr_increase_trump, _ = pearsonr(Trump, roi) print(corr_increase_clinton) print(corr_increase_trump) # time of maximum increase corr_time_max_clinton, _ = pearsonr(Clinton, timemax) corr_time_max_trump,_ = pearsonr(Trump, timemax) print(corr_time_max_clinton) print(corr_time_max_trump)

ValueError: array must not contain infs or NaNs

#heatmap of correlation ax = sns.heatmap( correlation, vmin=-1, vmax=1, center=0, cmap=sns.diverging_palette(20, 220, n=200), square=True ) ax.set_xticklabels( ax.get_xticklabels(), rotation=45, horizontalalignment='right' );

# Generate a mask for the upper triangle mask = np.triu(np.ones_like(correlation, dtype=bool)) # Set up the matplotlib figure f, ax = plt.subplots(figsize=(11, 9)) # Generate a custom diverging colormap cmap = sns.diverging_palette(230, 20, as_cmap=True) # Draw the heatmap with the mask and correct aspect ratio sns.heatmap(correlation, mask=mask, cmap=cmap, vmax=.3, center=0, square=True, linewidths=.5, cbar_kws={"shrink": .5})