GCP

# Cell 1
import pandas as pd
import os, sys
response_data = pd.read_csv('Downloads/Fire_Rescue_Responses.csv')
response_data.head()
rd_addr_loc = response_data['Location Address'].str.split('\n', 1, expand=True)
rd_addr_loc.columns = ['Address', 'Location']

rd_date = response_data['Response Date'].str.split(' ', 1, expand=True)
rd_date.columns = ['Date', 'Time']
rd = pd.merge(response_data, rd_addr_loc, right_index=True, left_index=True)
rd = pd.merge(rd, rd_date, right_index=True, left_index=True)
rd = rd[['Date', 'Response Type', 'Location Name', 'Address', 'Location']]
rd.to_csv('Downloads/responses.csv')
rd.head()

for call_type in res_df['Type'].unique():
display(call_type)
res_type = res_df[res_df['Type'] == call_type]
call_type_name = '{} Calls'.format(call_type)
#display(res_ems.head())
buckets = res_type.groupby('Consumption Categories')['Type'].count().reset_index()
buckets.columns = ['Consumption', call_type_name]
display(g = sns.factorplot(x=call_type_name , y="Consumption", data=buckets, size=6, kind="bar", palette="muted"))

Cell 1

#display(df['Consumption'].head())
consumption_min = df['Consumption'].min()
display("Consumption min: ", consumption_min)
consumption_max = df['Consumption'].max()
display("Consumption max: ", consumption_max)
consumption_median = df['Consumption'].median()
display("Consumption median: ", consumption_median)
consumption_std = df['Consumption'].std()
display("Consumption std: ", consumption_std)
display("Consumption count: ", df['Consumption'].shape[0])
consumption_mode = df['Consumption'].mode()
display("Consumption mode: ", consumption_mode)

List of outliers

consumption_outliers = df['Consumption'] < ( df['Consumption'].median() + 1 * consumption_std )
display(consumption_outliers.describe())
display(df['Consumption'].shape[0])
display(consumption_outliers.shape[0])
pd.options.display.float_format = '{:,.2f}'.format
#res_df = df[((df['Consumption'] - df['Consumption'].median()) / df['Consumption'].std()).abs() < 1]
res_df = df[(df['Consumption'] <= 5000)]
display("Residential: ", res_df['Consumption'].describe())
#com_df = df[((df['Consumption'] - df['Consumption'].median()) / df['Consumption'].std()).abs() >= 1]
com_df = df[(df['Consumption'] > 5000) &(df['Consumption'] < 200000)]
display("Commercial: ", com_df['Consumption'].describe())
pd.reset_option('^display.float_format', silent=True)

Cell 2

for call_type in res_df['Type'].unique():
display(call_type)
res_type = res_df[res_df['Type'] == call_type]
call_type_name = '{} Calls'.format(call_type)
#display(res_ems.head())
buckets = res_type.groupby('Consumption Categories')['Type'].count().reset_index()
buckets.columns = ['Consumption', call_type_name]
display(g = sns.factorplot(x=call_type_name , y="Consumption", data=buckets, size=6, kind="bar", palette="muted"))

call_corr = pd.DataFrame()
for call_type in res_df['Type'].unique():
#display(call_type)
res_type = res_df[res_df['Type'] == call_type]
call_type_name = '{} Calls'.format(call_type)
buckets = res_type.groupby('Consumption Categories')['Type'].count().reset_index()
buckets.columns = ['Consumption', call_type_name]
#display(buckets)
if len(call_corr.axes[0]) == 0:
display("Starting from", call_type_name)
call_corr = buckets
#display(call_corr)
else:
display("Adding data for", call_type_name)
call_corr = pd.merge(call_corr, buckets, right_index=True, left_index=True)
#display(call_corr)
calls_df = call_corr[['Consumption', 'EMS Calls', 'FIRE Calls', 'ALM Calls', 'SVC Calls', 'HAZ Calls']]
#calls_df.columns = ['Consumption', 'EMS', 'FIRE', 'ALM', 'SVC', 'HAZ']
#display(calls_df)
calls_only_df = calls_df[['EMS Calls', 'FIRE Calls', 'ALM Calls', 'SVC Calls', 'HAZ Calls']]
calls_only_df.corr(method='spearman')

EMS Calls	FIRE Calls	ALM Calls	SVC Calls	HAZ Calls

EMS Calls 1.000000 0.848759 0.525009 0.716986 0.808898
FIRE Calls 0.848759 1.000000 0.696650 0.571377 0.820447
ALM Calls 0.525009 0.696650 1.000000 0.331825 0.443817
SVC Calls 0.716986 0.571377 0.331825 1.000000 0.699963
HAZ Calls 0.808898 0.820447 0.443817 0.699963 1.000000