vijayanandrp

Accuracy of SGDClassifier (support vector machine - SVM) - 91.27829560585884

Accuracy (after tuning) of SGDClassifier (support vector machine - SVM) - 93.40878828229027

Grid Search best score -
0.974302171023

Grid Search best parameters -
{'clf__alpha': 0.0001,
 'tfidf__smooth_idf': False,

vijayanandrp

Accuracy of MultinomialNB (naive Bayes) - 83.48868175765645

Accuracy (after tuning) of MultinomialNB (naive Bayes) - 93.27563249001332

Grid Search best score -
0.979618963226

Grid Search best parameters -
{'clf__alpha': 0.001,
 'clf__fit_prior': False,

vijayanandrp

Accuracy of MultinomialNB (naive Bayes) - 83.48868175765645

Accuracy (after tuning) of MultinomialNB (naive Bayes) - 88.34886817576565

Grid Search best score -
0.945059813912

Grid Search best parameters -
{'clf__alpha': 0.5,
 'clf__fit_prior': False,

vijayanandrp

#!/usr/bin/env python3
# encoding: utf-8

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from sklearn.naive_bayes import MultinomialNB
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn import metrics
import numpy as np

vijayanandrp

Accuracy of SGDClassifier (support vector machine - SVM) - 91.27829560585884
Accuracy (after tuning) of SGDClassifier (support vector machine - SVM) - 91.27829560585884
Grid Search best score -
0.965440850687
Grid Search best parameters -
{'clf__alpha': 0.001, 'tfidf__use_idf': True, 'vect__ngram_range': (1, 1)}
Metrics classification report 
                        precision    recall  f1-score   support

           alt.atheism       0.95      0.81      0.87       319

vijayanandrp

#!/usr/bin/env python3
# encoding: utf-8

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from sklearn.linear_model import SGDClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline
from sklearn import metrics
import numpy as np

vijayanandrp

hilarious_text = ["Never interrupt your opponent while he's making a mistake.", "Sarcasm helps keep people from understanding you're saying what you really think of them.", "I once prayed to God for a bike, but quickly found out He didn't work that way—so I stole a bike and prayed for His forgiveness.", 'A train station is where the train stopsA bus station is where the bus stops. On my desk, I have a work station...', "You can't be late until you show up.", "War doesn't determine who's right—it determines who's left.", "If you think things can't get worse, it's probably only because you lack sufficient imagination.", 'Parents spend the first part of our lives teaching us to walk and talk and the rest of it telling us to sit down and shut up.', 'Expecting the world to treat you fairly because you are good is like expecting the bull not to charge because you are a vegetarian.', "Books have knowledge, knowledge is power, power corrupts, corruption is a crime, and crime doesn't paySo if you keep reading, you'll 

vijayanandrp

def linkify(html):
    check = ['https://', 'http://', 'www.', '.jpg', '.png', '.jpeg', '.gif']
    html_source = html
    replace = {}
    text = []
    for letter in html:
        if letter == '>':
            start = True
            continue
        elif letter == '<':

vijayanandrp

# you can write to stdout for debugging purposes, e.g.
# print "this is a debug message"

def solution(A):
    # write your code in Python 2.7
    # input validation

    # empty input
    if not len(A):
        return 1

vijayanandrp

# you can write to stdout for debugging purposes, e.g.
# print "this is a debug message"

def solution(A):
    # write your code in Python 2.7
    # input validation

    # empty input
    if not len(A):
        return 1