from model import m
from preprocessor import fr
import pandas as pd
import numpy as np
import pickle
import time

from sys import exit

from tensorflow.keras.utils import pad_sequences as kps

from matplotlib import pyplot as plt

from sklearn.metrics import f1_score, precision_score, recall_score, accuracy_score

from tqdm import tqdm
tqdm.pandas()


def __prep_conf_matr(data):
    output_matrix = np.zeros([2, 2])

    for p, r in data:
        output_matrix[int(p)][int(r)] += 1

    return output_matrix


def __plot_conf_matr(data):
    matr = __prep_conf_matr(data)

    _, ax = plt.subplots()

    ax.matshow(matr, cmap = plt.cm.Blues)

    for i, x in enumerate(matr):
        for j, y in enumerate(x):
            ax.text(i,
                    j,
                    str(round(y)),
                    va = "center",
                    ha = "center")

    plt.show()

m.load_weights("model2.keras")
tk = pickle.load(open('tokenizer.pickle', 'rb'))

d = pd.read_csv("yelp_review_polarity_csv/test.csv", header = None, names = ['e', 'c'])
c = d['c']
e = d['e'] - 1
c.progress_apply(fr)

s = tk.texts_to_sequences(c)
ps = kps(s, maxlen = 100)

p = m.predict(ps, batch_size = 1024)

data = [(i >= 0.5, v >= 0.5) for i, v in zip(p, e)]
__plot_conf_matr(data)

p = [i >= 0.5 for i in p]
r = [i >= 0.5 for i in e]

print(f"Accuracy  : {accuracy_score(p, r)}")
print(f"Precision : {precision_score(p, r, average = 'binary')}")
print(f"Recall    : {recall_score(p, r, average = 'binary')}")
print(f"F1 Score  : {f1_score(p, r, average = 'binary')}")