correlation.py

import pandas as pd

train_features = pd.read_csv('Data/dengue_features_train.csv',
                             index_col=[0,1,2])

train_labels = pd.read_csv('Data/dengue_labels_train.csv',
                           index_col=[0,1,2])

# Seperate data for San Juan
sj_train_features = train_features.loc['sj']
sj_train_labels = train_labels.loc['sj']

# Separate data for Iquitos
iq_train_features = train_features.loc['iq']
iq_train_labels = train_labels.loc['iq']

# Remove `week_start_date` string.
sj_train_features.drop('week_start_date', axis=1, inplace=True)
iq_train_features.drop('week_start_date', axis=1, inplace=True)

sj_train_features.fillna(method='ffill', inplace=True)
iq_train_features.fillna(method='ffill', inplace=True)


sj_train_features['total_cases'] = sj_train_labels.total_cases
iq_train_features['total_cases'] = iq_train_labels.total_cases


sj_correlations = sj_train_features.corr()
iq_correlations = iq_train_features.corr()


(sj_correlations
     .total_cases
     .drop('total_cases') # don't compare with myself
     .sort_values(ascending=False)
     .plot
     .barh())