File size: 3,627 Bytes
7a53047 |
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 |
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
import tensorflow as tf
from sklearn.metrics import classification_report, confusion_matrix, accuracy_score
print("---------------------- Downloading Dataset -------------------------\n")
dataset = pd.read_csv('https://raw.githubusercontent.com/adityaiiitmk/Datasets/master/SMSSpamCollection',sep='\t',names=['label','message'])
print("---------------------- -------------------------\n")
print(dataset.head())
print("---------------------- -------------------------")
print(dataset.groupby('label').describe())
print("---------------------- -------------------------")
dataset['label'] = dataset['label'].map( {'spam': 1, 'ham': 0} )
X = dataset['message'].values
y = dataset['label'].values
print("---------------------- Train Test Split -------------------------\n")
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
tokeniser = tf.keras.preprocessing.text.Tokenizer()
tokeniser.fit_on_texts(X_train) #learn vocabulary assigning unique int to each word
encoded_train = tokeniser.texts_to_sequences(X_train)
encoded_test = tokeniser.texts_to_sequences(X_test)
print(encoded_train[0:2])
print("---------------------- Padding -------------------------\n")
max_length = 10 #legth of sequence
padded_train = tf.keras.preprocessing.sequence.pad_sequences(encoded_train, maxlen=max_length, padding='post')
padded_test = tf.keras.preprocessing.sequence.pad_sequences(encoded_test, maxlen=max_length, padding='post')
print(padded_train[0:2])
print("---------------------- -------------------------\n")
vocab_size = len(tokeniser.word_index)+1
# define the model
print("---------------------- Modelling -------------------------\n")
model=tf.keras.models.Sequential([
tf.keras.layers.Embedding(input_dim=vocab_size,output_dim= 24, input_length=max_length),
tf.keras.layers.SimpleRNN(24, return_sequences=False), #return last time output
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dense(32, activation='relu'),
tf.keras.layers.Dense(1, activation='sigmoid')
])
# compile the model
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
print("---------------------- -------------------------\n")
# summarize the model
print(model.summary())
print("---------------------- -------------------------\n")
early_stop = tf.keras.callbacks.EarlyStopping(monitor='accuracy', mode='min', patience=10) #callback set of functions can applied different stages of training
print("---------------------- Training -------------------------\n")
# fit the model
model.fit(x=padded_train,
y=y_train,
epochs=50,
validation_data=(padded_test, y_test),
callbacks=[early_stop]
)
print("---------------------- -------------------------\n")
def c_report(y_true, y_pred):
print("Classification Report")
print(classification_report(y_true, y_pred))
acc_sc = accuracy_score(y_true, y_pred)
print(f"Accuracy : {str(round(acc_sc,2)*100)}")
return acc_sc
def plot_confusion_matrix(y_true, y_pred):
mtx = confusion_matrix(y_true, y_pred)
sns.heatmap(mtx, annot=True, fmt='d', linewidths=.5, cmap="Blues", cbar=False)
plt.ylabel('True label')
plt.xlabel('Predicted label')
plt.savefig(r"C:\Users\Dell\Documents\Sem !!!\Deep Learning\App\Results\test.jpg")
preds = (model.predict(padded_test) > 0.5).astype("int32")
c_report(y_test, preds)
plot_confusion_matrix(y_test, preds)
model.save("RNN/results/model/spam_model")
|