5

analyze.py

@@ -0,0 +1,68 @@
+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')}")