Spaces:
No application file
No application file
File size: 4,121 Bytes
2f5e00f efb524b 2f5e00f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 |
import time
import pickle
import tensorflow as tf
import pandas as pd
import tqdm
import numpy as np
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.callbacks import ModelCheckpoint, TensorBoard
from sklearn.model_selection import train_test_split
#from tensorflow.keras.layers import Embedding, Dropout, Dense
from tensorflow.keras.models import Sequential
#from tensorflow.keras.metrics import Recall, Precision
from sklearn.metrics import f1_score, precision_score, accuracy_score, recall_score
from tensorflow.keras.layers import Conv1D, GlobalMaxPooling1D, Dropout, Dense, Input, Embedding, MaxPooling1D, Flatten
SEQUENCE_LENGTH = 500 # the length of all sequences (number of words per sample)
EMBEDDING_SIZE = 100 # Using 100-Dimensional GloVe embedding vectors
TEST_SIZE = 0.25 # ratio of testing set
BATCH_SIZE = 64
EPOCHS = 10 # number of epochs
maxlen = 80
batch_size = 32
label2int = {"frustrated": 0, "negative": 1,"neutral":2,"positive":3,"satisfied":4}
int2label = {0: "frustrated", 1: "negative",2:"neutral",3:"positive",4:"satisfied"}
def load_data():
"""
Loads SMS Spam Collection dataset
"""
data = pd.read_csv("train.csv",encoding='latin-1')
texts = data['feedback'].values
labels=data['sentiment'].values
return texts, labels
def dl_evaluation_process():
print("loading data")
X, y = load_data()
# Text tokenization
# vectorizing text, turning each text into sequence of integers
tokenizer = Tokenizer()
tokenizer.fit_on_texts(X)
# lets dump it to a file, so we can use it in testing
pickle.dump(tokenizer, open("tokenizer.pickle", "wb"))
# convert to sequence of integers
X = tokenizer.texts_to_sequences(X)
# convert to numpy arrays
X = np.array(X)
y = np.array(y)
# pad sequences at the beginning of each sequence with 0's
# for example if SEQUENCE_LENGTH=4:
# [[5, 3, 2], [5, 1, 2, 3], [3, 4]]
# will be transformed to:
# [[0, 5, 3, 2], [5, 1, 2, 3], [0, 0, 3, 4]]
X = pad_sequences(X, maxlen=SEQUENCE_LENGTH)
# One Hot encoding labels
# [spam, ham, spam, ham, ham] will be converted to:
# [1, 0, 1, 0, 1] and then to:
# [[0, 1], [1, 0], [0, 1], [1, 0], [0, 1]]
y = [label2int[label] for label in y]
y = to_categorical(y)
# split and shuffle
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=TEST_SIZE, random_state=7)
# print our data shapes
'''print("X_train.shape:", X_train.shape)
print("X_test.shape:", X_test.shape)
print("y_train.shape:", y_train.shape)
print("y_test.shape:", y_test.shape)'''
#print("EMD Matrix")
print("Starting...")
# Define the model
print('Build model...')
model = Sequential()
model.add(Flatten(input_shape=(500,)))
model.add(Dense(128, activation='relu'))
model.add(Dense(5, activation='softmax'))
# Compile the model
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
# Train the model
print('Train...')
model.fit(X, y,
batch_size=batch_size,
epochs=20,
validation_data=(X_test, y_test))
y_test = np.argmax(y_test, axis=1)
y_pred = np.argmax(model.predict(X_test), axis=1)
acc = accuracy_score(y_test, y_pred) * 100
precsn = precision_score(y_test, y_pred, average="macro") * 100
recall = recall_score(y_test, y_pred, average="macro") * 100
f1score = f1_score(y_test, y_pred, average="macro") * 100
print("acc=", acc)
print("precsn=", precsn)
print("recall=", recall)
print("f1score=", f1score)
return acc, precsn, recall, f1score
if __name__ == '__main__':
dl_evaluation_process() |