Upload utilities.py

utilities.py

@@ -0,0 +1,65 @@
+import csv
+import numpy as np
+import nltk
+
+words_to_nums = {}
+
+def get_data_for_training(filename):
+    raw_data = open(filename, 'rt')
+    reader = csv.reader(raw_data, delimiter=',')
+    return list(reader)
+
+
+def get_data_and_labels(raw_data):
+    labels = np.array(raw_data)
+    labels = np.delete(labels, (0), axis=0)
+    labels = np.delete(labels, (0), axis=1)
+    labels = labels[:, 0]
+    for i, label in enumerate(labels):
+        labels[i] = 1 if (label == 'positive') else 0
+    labels = np.array(labels).astype('int')
+    del raw_data[0]
+    for j in raw_data:
+        del j[0]
+        del j[0]
+    for i in range(len(raw_data)):
+        raw_data[i] = nltk.word_tokenize(raw_data[i][0])
+    return raw_data, labels
+
+
+def get_word_embeddings(sentences):
+    counter = 0
+    data = []
+    for words in sentences:
+        num = []
+        for word in words:
+            if word not in words_to_nums:
+                words_to_nums[word] = counter
+                num.append(counter)
+                counter = counter+1
+            else:
+                num.append(words_to_nums[word])
+        data.append(num)
+
+    data = np.array(data, dtype=object)
+    return data
+
+
+def vectorize_sequence(sequences, dimensions):
+    results = np.zeros((len(sequences), dimensions))
+    for i, sequence in enumerate(sequences):
+        results[i, sequence] = 1.
+    return results
+
+def get_sequence(text):
+    text_input = nltk.word_tokenize(text)
+    sequence = []
+    for word in text_input:
+        if word not in words_to_nums:
+            continue
+        else:
+            sequence.append(words_to_nums[word])
+    testdata = []
+    testdata.append(sequence)
+    sequence = np.array(testdata)
+    return sequence