Created
May 14, 2017 19:39
-
-
Save DhavalThkkar/2bb566b7d02a2d26bae99d662f8b8f2f to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import numpy as np | |
import sys | |
from datetime import datetime | |
# Slearn for easy label encoding, textblob for senitment reference | |
from sklearn.preprocessing import LabelEncoder | |
from sklearn.feature_extraction.text import CountVectorizer | |
from sklearn.model_selection import StratifiedKFold | |
from sklearn.cross_validation import train_test_split | |
from sklearn.ensemble import RandomForestClassifier | |
from sklearn.naive_bayes import MultinomialNB | |
from sklearn.metrics import roc_curve, auc | |
# Keras | |
from keras.models import Sequential | |
from keras.layers import Dense, Dropout | |
from keras.optimizers import SGD | |
# ML Models | |
from sklearn.utils import shuffle | |
# NLP toolkits | |
import nltk, re | |
from nltk.stem import WordNetLemmatizer, PorterStemmer | |
#nltk.download() | |
import string | |
/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20. | |
"This module will be removed in 0.20.", DeprecationWarning) | |
Using TensorFlow backend. | |
Importing Data... | |
Cleaning Tweets... 116%Elapsed Time: {}'.format(datetime.now()-t0))Cleaning Tweets... | |
Training Models... | |
__________________________________________________________________ | |
k-1: Resampling Accuracy: 73.8% Original Accuracy: 72.1% | |
Resampling AUC Score: 0.819 Original AUC Score: 0.807 | |
__________________________________________________________________ | |
k-2: Resampling Accuracy: 73.1% Original Accuracy: 72.8% | |
Resampling AUC Score: 0.804 Original AUC Score: 0.809 | |
__________________________________________________________________ | |
k-3: Resampling Accuracy: 75.6% Original Accuracy: 73.8% | |
Resampling AUC Score: 0.811 Original AUC Score: 0.813 | |
__________________________________________________________________ | |
k-4: Resampling Accuracy: 74.8% Original Accuracy: 72.8% | |
Resampling AUC Score: 0.816 Original AUC Score: 0.809 | |
__________________________________________________________________ | |
k-5: Resampling Accuracy: 73.2% Original Accuracy: 72.6% | |
Resampling AUC Score: 0.793 Original AUC Score: 0.809 | |
__________________________________________________________________ | |
k-6: Resampling Accuracy: 73.6% Original Accuracy: 73.3% | |
Resampling AUC Score: 0.805 Original AUC Score: 0.810 | |
__________________________________________________________________ | |
k-7: Resampling Accuracy: 72.2% Original Accuracy: 72.1% | |
Resampling AUC Score: 0.793 Original AUC Score: 0.806 | |
__________________________________________________________________ | |
k-8: Resampling Accuracy: 75.3% Original Accuracy: 72.7% | |
Resampling AUC Score: 0.825 Original AUC Score: 0.809 | |
__________________________________________________________________ | |
k-9: Resampling Accuracy: 73.7% Original Accuracy: 72.8% | |
Resampling AUC Score: 0.812 Original AUC Score: 0.806 | |
__________________________________________________________________ | |
k-10: Resampling Accuracy: 74.2% Original Accuracy: 72.9% | |
Resampling AUC Score: 0.810 Original AUC Score: 0.811 | |
Total Elapsed Time: 0:00:14.850715 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment