Spam.py

# coding: utf-8

# In[3]:


# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load in 

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory

from subprocess import check_output
print(check_output(["ls", "D:/"]).decode("utf8"))

# Any results you write to the current directory are saved as output.


# In[4]:


DATA_FILE = '../input/spam.csv'
df = pd.read_csv(DATA_FILE,encoding='latin-1')
print(df.head())

tags = df.v1
texts = df.v2
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.layers import Embedding
from keras.layers import Conv1D, GlobalMaxPooling1D
from keras.preprocessing.text import Tokenizer
from keras.preprocessing import sequence
from sklearn.preprocessing import LabelEncoder
import time
from keras import metrics
print('import done')


# In[5]:


num_max = 1000
# preprocess
le = LabelEncoder()
tags = le.fit_transform(tags)
tok = Tokenizer(num_words=num_max)
tok.fit_on_texts(texts)
mat_texts = tok.texts_to_matrix(texts,mode='count')
print(tags[:5])
print(mat_texts[:5])
print(tags.shape,mat_texts.shape)


# In[6]:


# try a simple model first

def get_simple_model():
    model = Sequential()
    model.add(Dense(512, activation='relu', input_shape=(num_max,)))
    model.add(Dropout(0.2))
    model.add(Dense(256, activation='relu'))
    model.add(Dropout(0.2))
    model.add(Dense(1, activation='sigmoid'))
    model.summary()
    model.compile(loss='binary_crossentropy',
              optimizer='adam',
              metrics=['acc',metrics.binary_accuracy])
    print('compile done')
    return model

def check_model(model,x,y):
    model.fit(x,y,batch_size=32,epochs=10,verbose=1,validation_split=0.2)

m = get_simple_model()
check_model(m,mat_texts,tags)


# In[7]:


# for cnn preproces
max_len = 100
cnn_texts_seq = tok.texts_to_sequences(texts)
print(cnn_texts_seq[0])
cnn_texts_mat = sequence.pad_sequences(cnn_texts_seq,maxlen=max_len)
print(cnn_texts_mat[0])
print(cnn_texts_mat.shape)


# In[8]:


def get_cnn_model_v1():   
    model = Sequential()
    # we start off with an efficient embedding layer which maps
    # our vocab indices into embedding_dims dimensions
    # 1000 is num_max
    model.add(Embedding(1000,
                        20,
                        input_length=max_len))
    model.add(Dropout(0.2))
    model.add(Conv1D(64,
                     3,
                     padding='valid',
                     activation='relu',
                     strides=1))
    model.add(GlobalMaxPooling1D())
    model.add(Dense(256))
    model.add(Dropout(0.2))
    model.add(Activation('relu'))
    model.add(Dense(1))
    model.add(Activation('sigmoid'))
    model.summary()
    model.compile(loss='binary_crossentropy',
                  optimizer='adam',
                  metrics=['acc',metrics.binary_accuracy])
    return model

m = get_cnn_model_v1()
check_model(m,cnn_texts_mat,tags)


# In[9]:


def get_cnn_model_v2(): # added embed   
    model = Sequential()
    # we start off with an efficient embedding layer which maps
    # our vocab indices into embedding_dims dimensions
    # 1000 is num_max
    model.add(Embedding(1000,
                        50, #!!!!!!!!!!!!!!!!!!!!!!!
                        input_length=max_len))
    model.add(Dropout(0.2))
    model.add(Conv1D(64,
                     3,
                     padding='valid',
                     activation='relu',
                     strides=1))
    model.add(GlobalMaxPooling1D())
    model.add(Dense(256))
    model.add(Dropout(0.2))
    model.add(Activation('relu'))
    model.add(Dense(1))
    model.add(Activation('sigmoid'))
    model.summary()
    model.compile(loss='binary_crossentropy',
                  optimizer='adam',
                  metrics=['acc',metrics.binary_accuracy])
    return model

m = get_cnn_model_v2()
check_model(m,cnn_texts_mat,tags)


# In[10]:


def get_cnn_model_v3():    # added filter
    model = Sequential()
    # we start off with an efficient embedding layer which maps
    # our vocab indices into embedding_dims dimensions
    # 1000 is num_max
    model.add(Embedding(1000,
                        20,
                        input_length=max_len))
    model.add(Dropout(0.2))
    model.add(Conv1D(256, #!!!!!!!!!!!!!!!!!!!
                     3,
                     padding='valid',
                     activation='relu',
                     strides=1))
    model.add(GlobalMaxPooling1D())
    model.add(Dense(256))
    model.add(Dropout(0.2))
    model.add(Activation('relu'))
    model.add(Dense(1))
    model.add(Activation('sigmoid'))
    model.summary()
    model.compile(loss='binary_crossentropy',
                  optimizer='adam',
                  metrics=['acc',metrics.binary_accuracy])
    return model

m = get_cnn_model_v3()
check_model(m,cnn_texts_mat,tags)


# In[ ]:





# In[ ]: