#!/usr/bin/python3

import pandas as pd
import csv
import pickle
import numpy as np

def predict():
    dev0 = pd.read_csv("dev-0/in.tsv", delimiter="\t", header=None, names=["document","date"], quoting=csv.QUOTE_NONE)["document"]
    testA = pd.read_csv("test-A/in.tsv", delimiter="\t", header=None, names=["document","date"], quoting=csv.QUOTE_NONE)["document"]

    clf = pickle.load(open("clf.model", "rb"))
    vectorizer = pickle.load(open("vectorizer.model", "rb"))
    
    dev0_vectorizer = vectorizer.transform(dev0)
    testA_vectorizer = vectorizer.transform(testA)

    y_dev = clf.predict_proba(dev0_vectorizer)[:, 1]
    y_test = clf.predict_proba(testA_vectorizer)[:, 1]

    np.savetxt('test-A/out.tsv', y_test, '%f')
    np.savetxt('dev-0/out.tsv', y_dev, '%f')

predict()