In [ ]:
import nltk
import sklearn
import matplotlib
#print('The nltk version is {}.'.format(nltk.__version__))
#print('The scikit-learn version is {}.'.format(sklearn.__version__))
#print('The matplotlib version is {}.'.format(matplotlib.__version__))
In [ ]:
import sys
import numpy as np
import cPickle
from time import time
from sklearn import model_selection
# from sklearn import cross_validation
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_selection import SelectPercentile, f_classif
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt
%matplotlib inline
from collections import Counter
In [ ]:
def train_predict(desc):
print
print
print ("Please await, processing the result:", str(desc))
print
##Reduce DataSet (1%)
features_train_small = features_train[:len(features_train)/100]
labels_train_small = labels_train[:len(labels_train)/100]
t0 = time()
clf.fit(features_train_small, labels_train_small)
traintime = "Training time: " + str(round(time()-t0, 3))
t1 = time()
pred = clf.predict(features_test)
predtime = "Predicting time: " + str(round(time()-t1, 3))
print
print
print "********** Results for experiment: \"",desc,"\" ************"
print
print traintime, "s"
print predtime, "s"
plotgraph (pred,str(desc))
accuracy(labels_test, pred)
def train_predict_fulldataset(desc):
print
print
print ("Please await, processing the result:", str(desc))
print
t0 = time()
clf.fit(features_train, labels_train)
traintime = "Training time: " + str(round(time()-t0, 3))
t1 = time()
pred = clf.predict(features_test)
predtime = "Predicting time: " + str(round(time()-t1, 3))
print
print
print "********** Results for experiment: \"",desc,"\" ************"
print
print traintime, "s"
print predtime, "s"
plotgraph (pred,str(desc))
accuracy(labels_test, pred)
def grid_train_predict(desc):
print
print
print ("Please await, processing the result:", str(desc))
print
##Reduce DataSet (1%)
features_train_small = features_train[:len(features_train)/100]
labels_train_small = labels_train[:len(labels_train)/100]
t0 = time()
clf.fit(features_train_small, labels_train_small)
traintime = "Training time: " + str(round(time()-t0, 3))
t1 = time()
pred = clf.predict(features_test)
predtime = "Predicting time: " + str(round(time()-t1, 3))
print
print
print "********** Results for experiment: \"",desc,"\" ************"
print
print traintime, "s"
print predtime, "s"
plotgraph (pred,str(desc))
# accuracy(labels_test, pred)
def grid_train_predict_fulldataset(desc):
print
print
print ("Please await, processing the result:", str(desc))
print
t0 = time()
clf.fit(features_train, labels_train)
traintime = "Training time: " + str(round(time()-t0, 3))
t1 = time()
pred = clf.predict(features_test)
predtime = "Predicting time: " + str(round(time()-t1, 3))
print
print
print "********** Results for experiment: \"",desc,"\" ************"
print
print traintime, "s"
print predtime, "s"
plotgraph (pred,str(desc))
# accuracy(labels_test, pred)
def plotgraph (pred, desc):
c = Counter(pred)
men = c[1]
print
print "Number of Predicted emails for Chris", men
women = c[0]
print "Number of Predicted emails for Sara", women
bar_heights = (men, women)
x = (1, 2)
fig, ax = plt.subplots()
width = 0.4
ax.bar(x, bar_heights, width)
ax.set_xlim((0, 3))
ax.set_ylim((0, max(men, women)*1.1))
ax.set_xticks([i+width/2 for i in x])
ax.set_xticklabels(['Cris', 'Sarah'])
plt.show()
def accuracy(labels_test, pred):
accuracy = accuracy_score(labels_test, pred)
print "Total Accuracy:", accuracy
def preprocess(words_file = "../data/word_data.pkl", authors_file="../data/email_authors.pkl"):
"""
this function takes a pre-made list of email texts (by default word_data.pkl)
and the corresponding authors (by default email_authors.pkl) and performs
a number of preprocessing steps:
-- splits into training/testing sets (10% testing)
-- vectorizes into tfidf matrix
-- selects/keeps most helpful features
after this, the feaures and labels are put into numpy arrays, which play nice with sklearn functions
4 objects are returned:
-- training/testing features
-- training/testing labels
"""
### the words (features) and authors (labels), already largely preprocessed
### this preprocessing will be repeated in the text learning mini-project
word_data = cPickle.load( open("../data/word_data.pkl", "r"))
authors = cPickle.load( open("../data/email_authors.pkl", "r") )
### test_size is the percentage of events assigned to the test set (remainder go into training)
features_train, features_test, labels_train, labels_test = model_selection.train_test_split(word_data, authors, test_size=0.1, random_state=42)
### text vectorization--go from strings to lists of numbers
vectorizer = TfidfVectorizer(sublinear_tf=True, max_df=0.5,
stop_words='english')
features_train_transformed = vectorizer.fit_transform(features_train)
features_test_transformed = vectorizer.transform(features_test)
### feature selection, because text is super high dimensional and
### can be really computationally chewy as a result
selector = SelectPercentile(f_classif, percentile=1)
selector.fit(features_train_transformed, labels_train)
features_train_transformed = selector.transform(features_train_transformed).toarray()
features_test_transformed = selector.transform(features_test_transformed).toarray()
### info on the data
print
print "Number of available emails to be trained for Chris:", sum(labels_train)
print "Number of available emails to be trained for Sara:", len(labels_train)-sum(labels_train)
return features_train_transformed, features_test_transformed, labels_train, labels_test
In [ ]:
features_train, features_test, labels_train, labels_test = preprocess()