#!/usr/bin/env python
# coding: utf-8

# In[1]:


from collections import defaultdict, Counter
import csv
import regex as re
import pandas as pd
from nltk import trigrams, word_tokenize


# In[26]:

def prepare_data():
    x_train = pd.read_csv('train/in.tsv.xz', sep='\t',  header=None,
                          quoting=csv.QUOTE_NONE, nrows=70000, on_bad_lines='skip')
    y_train = pd.read_csv('train/expected.tsv', sep='\t', header=None,
                          quoting=csv.QUOTE_NONE, nrows=70000, on_bad_lines='skip')
    x_train = x_train[[6, 7]]
    x_train = pd.concat([x_train, y_train], axis=1)
    x_train['l'] = x_train[6] + x_train[0] + x_train[7]

    return x_train, y_train


x_train, y_train = prepare_data()


# In[39]:


def train(x_train):
    model = defaultdict(lambda: defaultdict(lambda: 0))
    setOf = set()
    alpha = 0.02
    count = x_train.iterrows()
    for i, (_, row) in enumerate(count):
        text = re.sub(r'\p{P}', '', str(row['l']).lower().replace(
            '-\\n', '').replace('\\n', ' '))
        words = word_tokenize(text)
        for word_1, word_2, word_3 in trigrams(words, pad_right=True, pad_left=True):
            if word_1 and word_2 and word_3:
                model[(word_1, word_3)][word_2] += 1
                setOf.add(word_1)
                setOf.add(word_2)
                setOf.add(word_3)

    for words in model:
        num_n_grams = float(sum(model[words].values()))
        for word in model[words]:
            model[words][word] = (model[words][word] + alpha) / \
                (num_n_grams + alpha * len(setOf))

    return model


# In[41]:


def predict(before, after):
    result = ''
    p = 0.0
    pred = dict(Counter(dict(model[before, after])).most_common(7))
    for key, value in pred.items():
        p += value
        result += f'{key}:{value} '
    if p == 0.0:
        result = 'to:0.02 the:0.02 be:0.02 and:0.01 or:0.01 and:0.01 a:0.01 :0.9'
        return result
    result += f':{max(1 - p, 0.01)}'

    return result


# In[42]:
def preprocess(text):
    text = text.lower().replace('-\\n', '').replace('\\n', ' ')
    return re.sub(r'\p{P}', '', text)


def gap_predict(file):
    X_test = pd.read_csv(f'{file}/in.tsv.xz', sep='\t', header=None,
                         quoting=csv.QUOTE_NONE,  error_bad_lines=False)
    with open(f'{file}/out.tsv', 'w', encoding='utf-8') as result_file:
        for _, row in X_test.iterrows():
            before, after = word_tokenize(preprocess(
                str(row[6]))), word_tokenize(preprocess(str(row[7])))
            if len(before) < 3 or len(after) < 3:
                result = 'to:0.02 the:0.02 be:0.02 and:0.01 or:0.01 and:0.01 a:0.01 :0.9'
            else:
                result = predict(before[-1], after[0])
            result_file.write(result + '\n')


# In[43]:


model = train(x_train)
gap_predict('dev-0')
gap_predict('test-A')