Does temperature affect crimes being committed?

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

weather = pd.read_csv('san_fran_weather.csv') weather["DATE"]= pd.to_datetime(weather["DATE"],format="%d/%m/%Y") #dt.datetime.strptime('2018-05-12','%Y-%m-%d').strftime('%Y-%m-%d') weather.info() weather.head()

weather_new=weather[weather['DATE']>='2018'] weather_new.info() weather_new.tail()

crimes = pd.read_csv('san_fran_crime_18_21.csv') #crimes["Incident Date"]= pd.to_datetime(crimes["Incident Date"]) crimes.info()

#crimes.sort_values('Incident Date').tail() #print(crimes[crimes['Incident Date']=='27/9/2021']) crimes["Incident Date"]= pd.to_datetime(crimes["Incident Date"],format="%d/%m/%Y") crimes.sort_values('Incident Date').tail()

crimes_grouped=crimes.groupby('Incident Date').size() crimes_df=pd.DataFrame(crimes_grouped) crimes_df = crimes_df.rename(columns={0: 'crimes'}) crimes_df.head()

weath_crim = weather_new.merge(crimes_df, left_on='DATE', right_on='Incident Date', how='left') weath_crim.info()

weath_crim.head()

number_of_missing_fin = weath_crim['crimes'].isna().sum() print(number_of_missing_fin)

average_temp = weath_crim['TAVG'].mean() max_temp=weath_crim['TAVG'].max() average_crime = weath_crim['crimes'].mean() print('The average # of crimes in SF is ', average_crime) print('The average temperature in SF is ', average_temp) print('The max average temp in SF over the 3 years is ', max_temp)

# comment: why not use TAVG as mean temperature instead of TMAX? # this part may be unnecessary for

sns.regplot(data = weath_crim, x = weath_crim['TAVG'],y = weath_crim['crimes']) plt.show()

# comment: why use TMAX instead of TAVG hahaha? # the graph does not show a very strong positive correlation

!pip install statsmodels

import statsmodels.api as sm # Fit and summarize OLS model mod = sm.OLS(weath_crim.TMAX, weath_crim.crimes) res = mod.fit() print(res.summary(alpha = 0.01))