In [ ]:

    

import pandas as pd


    

In [ ]:

    

raw_train_dataframe = pd.read_table('train.csv', sep='\t')
cleared_train_dataframe = raw_train_dataframe.drop('DSSR', axis=1).drop('pdb_chain', axis=1).dropna()
del raw_train_dataframe


    

In [ ]:

    

import numpy as np


    

In [ ]:

    

rows_count = cleared_train_dataframe.shape[0]
train_dataframe = cleared_train_dataframe.iloc[range(0, rows_count, 2), :]
del cleared_train_dataframe


    

In [ ]:

    

train_sample = train_dataframe.drop('mg', axis=1).values
train_sample_answers = train_dataframe['mg'].values
del train_dataframe


    

In [ ]:

    

from sklearn.ensemble import AdaBoostClassifier


    

In [ ]:

    

classifier = AdaBoostClassifier(n_estimators=1000)
classifier.fit(train_sample, train_sample_answers)
del train_sample
del train_sample_answers


    

In [ ]:

    

raw_test_dataframe = pd.read_table('test.csv', sep=',')
cleared_test_dataframe = raw_test_dataframe.drop('DSSR', axis=1).drop('pdb_chain', axis=1).drop('Id', axis=1).drop('index', axis=1).dropna()
del raw_test_dataframe


    

In [ ]:

    

test_sample = cleared_test_dataframe.values
del cleared_test_dataframe


    

In [ ]:

    

test_sample_answers = classifier.predict(test_sample).reshape(-1, 1)
del test_sample


    

In [ ]:

    

test_sample_answers.sum()


    

In [ ]:

    

submission = np.hstack([np.arange(len(test_sample_answers)).reshape(-1, 1), test_sample_answers])
del test_sample_answers


    

In [ ]:

    

import csv
with open('submission.csv', 'w', newline='') as csvfile:
    writer = csv.writer(csvfile, delimiter=',')
    writer.writerow(['Id', 'mg'])
    writer.writerows(submission)
    del writer
del submission