Update ML_Proj

ML_Proj

@@ -1,48 +1,4 @@
 
-def model_train_save(train_data):
-    Train_df = pd.read_csv(train_data,header = 0, delimiter = ',', encoding="iso-8859-1")
-    X_train = Train_df.text
-    y_train = Train_df.IndustryCategory
-    tokenizer = Tokenizer(num_words=5000)
-    tokenizer.fit_on_texts(X_train)
-    X_train = tokenizer.texts_to_sequences(X_train)
-    vocab_size = len(tokenizer.word_index) + 1  # Adding 1 because of reserved 0 index
-    maxlen = 100
-    X_train = pad_sequences(X_train, padding='post', maxlen=maxlen)
-    encoder = LabelEncoder()
-    encoder.fit(y_train)
-    y_train = encoder.transform(y_train)
-    num_classes = np.max(y_train) + 1
-    y_train = utils.to_categorical(y_train, num_classes)
-    embedding_dim = 50
-    model = Sequential()
-    model.add(layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim, input_length=maxlen))
-    model.add(layers.Flatten())
-    model.add(layers.Dense(10, activation='relu'))
-    model.add(layers.Dense(num_classes, activation='sigmoid'))
-    model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
-    model.summary()
-    history = model.fit(np.array(X_train), np.array(y_train),epochs=2,verbose=False,batch_size=10)
-    loss, Training_accuracy = model.evaluate(X_train, y_train, verbose=False)
-    print("Training Accuracy: {:.4f}".format(Training_accuracy))
-    # serialize model to JSON
-    #  the keras model which is trained is defined as 'model' 
-    model_json = model.to_json()
-    with open("model_num.json", "w") as json_file:
-        json_file.write(model_json)
-
-    # serialize weights to HDF5
-    model.save_weights("model_num.h5")
-    # load json and create model
-    json_file = open('model_num.json', 'r')
-    loaded_model_json = json_file.read()
-    json_file.close()
-    loaded_model = model_from_json(loaded_model_json)
-    # load weights into new model
-    loaded_model.load_weights("model_num.h5")
-    #print("Loaded model from disk")
-    return (loaded_model.save('model_num.hdf5'))
-
 def predict(test_data):
     Test_df = pd.read_csv(test_data,header = 0, delimiter = ',', encoding="iso-8859-1")
     X_test = Test_df.text