#generated from jupyter
# %%
import lzma
import sys
from io import StringIO
from sklearn.feature_extraction.text import TfidfVectorizer
import pandas as pd
import numpy

pathX = "./train/in.tsv.xz"
# pathX = "./train/in.tsv"
pathY = "./train/expected.tsv"
nrows = 10000

# %%
# data = lzma.open(pathX, mode='rt', encoding='utf-8').read()
# stringIO = StringIO(data)
# df = pd.read_csv(stringIO, sep="\t", header=None)
df = pd.read_csv(pathX, sep='\t', nrows=nrows, header=None)
df = df.drop(df.columns[1], axis=1)
topics = pd.read_csv(pathY, sep='\t', nrows=nrows, header=None)

# %%
print(len(df.index))

print(len(topics.index))


# %%
df.sample()

# %%
vectorizer = TfidfVectorizer(lowercase=True, stop_words=['english'])
X = vectorizer.fit_transform(df.to_numpy().ravel())
vectorizer.get_feature_names_out()


# %%
# vectorizer.transform("Ala ma kotka".lower().split())

# %%
df = df.reset_index()

# %%
tfidfVector = vectorizer.transform(df[0])

    

# %%
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB

gnb = GaussianNB()
gnb.fit(tfidfVector.todense(), topics)

# %%
testXPath = "./dev-0/in.tsv.xz"
testYPath = "./dev-0/expected.tsv"

testX = pd.read_csv(testXPath, sep='\t', nrows=nrows, header=None)

testY = pd.read_csv(testYPath, sep='\t', nrows=nrows, header=None)
testXtfidfVector = vectorizer.transform(testX[0])


# %%
testXPath = "./test-A/in.tsv.xz"
testYPath = "./test-A/expected.tsv"

testX = pd.read_csv(testXPath, sep='\t', nrows=nrows, header=None)

# testY = pd.read_csv(testYPath, sep='\t', nrows=nrows, header=None)
testXtfidfVector = vectorizer.transform(testX[0])


# %%
pred = gnb.predict(testXtfidfVector.todense())
print(pred)

import csv
with open(testYPath, 'w', newline='') as f_output:
    tsv_output = csv.writer(f_output, delimiter='\n')
    tsv_output.writerow(pred)