grohith327

import numpy as np 
from sklearn.model_selection import train_test_split

Y = []
for val in y:
    if(val == 0):
        Y.append([1,0])
    else:
        Y.append([0,1])
Y = np.array(Y)

grohith327

import pandas as pd
import numpy as np

file_path = '/Users/rohith/Documents/Datasets/SMS_Spam/spam.csv'
df = pd.read_csv(file_path)

out = df['v1']
text = df['v2']

label = []

grohith327

from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split

x_train = []
x_test = []
y_train = []
y_test = []

text, label = shuffle(text,label)
x_train, x_test, y_train, y_test = train_test_split(text,label,train_size=0.9)

grohith327

from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer

count_vect = CountVectorizer(decode_error='ignore')
x_train_count = count_vect.fit_transform(x_train)
tfidf_trans = TfidfTransformer()
x_train_tfidf = tfidf_trans.fit_transform(x_train_count)

x_test_count = count_vect.transform(x_test)
x_test_tfidf = tfidf_trans.transform(x_test_count)

grohith327

from xgboost import XGBClassifier
from sklearn.metrics import accuracy_score

clf = XGBClassifier(n_estimators=200)
clf.fit(x_train_tfidf,y_train)
y_pred = clf.predict(x_test_tfidf)
print(accuracy_score(y_test,y_pred))

grohith327

from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split
import numpy as np

X, Y = shuffle(X,Y)

x_train = []
y_train = []
x_test = []
y_test = []

grohith327

## Logistic Regression 
import numpy as np

def sigmoid(x):
    return (1 / (1 + np.exp(-x)))

m = 90
alpha = 0.0001

theta_0 = np.zeros((m,1))

grohith327

from sklearn.metrics import accuracy_score

test_x_1 = x_test[:,0]
test_x_2 = x_test[:,1]
test_x_3 = x_test[:,2]
test_x_4 = x_test[:,3]

test_x_1 = np.array(test_x_1)
test_x_2 = np.array(test_x_2)
test_x_3 = np.array(test_x_3)

grohith327

import matplotlib.pyplot as plt 

cost_func = np.array(cost_func)
cost_func = cost_func.reshape(10000,1)
plt.plot(range(len(cost_func)),cost_func)

grohith327

from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression

clf = LogisticRegression()
clf.fit(x_train,y_train)
y_pred = clf.predict(x_test)
print(accuracy_score(y_test,y_pred))