import jovian

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from collections import Counter
from sklearn import feature_extraction, model_selection, naive_bayes, metrics, svm
from IPython.display import Image
import warnings
warnings.filterwarnings("ignore")
%matplotlib inline  

data=pd.read_csv(r"spam.csv",encoding='latin-1')
print(data.head(10))

count_Class=pd.value_counts(data["v1"], sort= True)
count_Class.plot(kind= 'bar', color= ["blue", "orange"])
plt.title('Bar chart')
plt.show()

count_Class.plot(kind = 'pie',  autopct='%1.0f%%')
plt.title('Pie chart')
plt.ylabel('')
plt.show()

count1 = Counter(" ".join(data[data['v1']=='ham']["v2"]).split()).most_common(20)
df1 = pd.DataFrame.from_dict(count1)
df1 = df1.rename(columns={0: "words in non-spam", 1 : "count"})
count2 = Counter(" ".join(data[data['v1']=='spam']["v2"]).split()).most_common(20)
df2 = pd.DataFrame.from_dict(count2)
df2 = df2.rename(columns={0: "words in spam", 1 : "count_"})

df1.plot.bar(legend = False)
y_pos = np.arange(len(df1["words in non-spam"]))
plt.xticks(y_pos, df1["words in non-spam"])
plt.title('More frequent words in non-spam messages')
plt.xlabel('words')
plt.ylabel('number')
plt.show()

df2.plot.bar(legend = False, color = 'orange')
y_pos = np.arange(len(df2["words in spam"]))
plt.xticks(y_pos, df2["words in spam"])
plt.title('More frequent words in spam messages')
plt.xlabel('words')
plt.ylabel('number')
plt.show()

f = feature_extraction.text.CountVectorizer(stop_words = 'english')
X = f.fit_transform(data["v2"])
np.shape(X)

data["v1"]=data["v1"].map({'spam':1,'ham':0})
print(data)
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, data['v1'], test_size=0.33, random_state=42)
print([np.shape(X_train), np.shape(X_test)])

#
list_alpha = np.arange(1/100000, 20, 0.11)
score_train = np.zeros(len(list_alpha))
score_test = np.zeros(len(list_alpha))
recall_test = np.zeros(len(list_alpha))
precision_test= np.zeros(len(list_alpha))
count = 0
for alpha in list_alpha:
    bayes = naive_bayes.MultinomialNB(alpha=alpha)
    bayes.fit(X_train, y_train)
    score_train[count] = bayes.score(X_train, y_train)
    score_test[count]= bayes.score(X_test, y_test)
    recall_test[count] = metrics.recall_score(y_test, bayes.predict(X_test))
    precision_test[count] = metrics.precision_score(y_test, bayes.predict(X_test))
    count = count + 1 

matrix = np.matrix(np.c_[list_alpha, score_train, score_test, recall_test, precision_test])
models = pd.DataFrame(data = matrix, columns = 
             ['alpha', 'Train Accuracy', 'Test Accuracy', 'Test Recall', 'Test Precision'])
models.head(n=10)

best_index = models['Test Precision'].idxmax()
models.iloc[best_index, :]

models[models['Test Precision']==1].head(n=5)

best_index = models[models['Test Precision']==1]['Test Accuracy'].idxmax()
bayes = naive_bayes.MultinomialNB(alpha=list_alpha[best_index])
bayes.fit(X_train, y_train)
models.iloc[best_index, :]

m_confusion_test = metrics.confusion_matrix(y_test, bayes.predict(X_test))
pd.DataFrame(data = m_confusion_test, columns = ['Predicted 0', 'Predicted 1'],
            index = ['Actual 0', 'Actual 1'])

list_C = np.arange(500, 2000, 100) #100000
score_train = np.zeros(len(list_C))
score_test = np.zeros(len(list_C))
recall_test = np.zeros(len(list_C))
precision_test= np.zeros(len(list_C))
count = 0
for C in list_C:
    svc = svm.SVC(C=C)
    svc.fit(X_train, y_train)
    score_train[count] = svc.score(X_train, y_train)
    score_test[count]= svc.score(X_test, y_test)
    recall_test[count] = metrics.recall_score(y_test, svc.predict(X_test))
    precision_test[count] = metrics.precision_score(y_test, svc.predict(X_test))
    count = count + 1 

matrix = np.matrix(np.c_[list_C, score_train, score_test, recall_test, precision_test])
models = pd.DataFrame(data = matrix, columns = 
             ['C', 'Train Accuracy', 'Test Accuracy', 'Test Recall', 'Test Precision'])
models.head(n=10)

best_index = models['Test Precision'].idxmax()
models.iloc[best_index, :]

models[models['Test Precision']==1].head(n=5)

best_index = models[models['Test Precision']==1]['Test Accuracy'].idxmax()
svc = svm.SVC(C=list_C[best_index])
svc.fit(X_train, y_train)
models.iloc[best_index, :]

m_confusion_test = metrics.confusion_matrix(y_test, svc.predict(X_test))
pd.DataFrame(data = m_confusion_test, columns = ['Predicted 0', 'Predicted 1'],
            index = ['Actual 0', 'Actual 1'])

from sklearn.feature_extraction import DictVectorizer
from keras.models import load_model


mytest=("Mobile no. has won 500000 ")
Y = [mytest]#mytest is a new email in string format
f = feature_extraction.text.CountVectorizer(stop_words = 'english')

f.fit(data["v2"]) # fittingf

X = f.transform(Y)
res=bayes.predict(X)
print(res)

jovian.commit(artifacts=['spam.csv'])