In [1]:

    

import glob
from functools import reduce

import pandas as pd


    

In [2]:

    

path = '../data/results/'
files = glob.glob(path + "/*.csv")
dfs = []
for file in files:
    df = pd.read_csv(file, index_col=None, header=0)
    dfs.append(df)

df = reduce(lambda left,right: pd.merge(left,right,on='Id'), dfs)


    

In [3]:

    

results_cols = ['results_' + str(n) for n in range(len(dfs))]


    

In [4]:

    

df.columns = ['Id'] + results_cols


    

In [5]:

    

df['Category'] = df[results_cols].mode(axis=1)[0].astype(int)


    

In [6]:

    

output = df[['Id', 'Category']]


    

In [7]:

    

output.to_csv('../data/ensemble00.csv', index=False)


    

In [ ]: