Sanket sdoshi579

Trying to make computers think like humans.

sdoshi579 / NLP Basics

Last active January 21, 2019 18:17

Natural Language Processing Basics Uses Nltk package and shows tokenization and lemmatization


	import nltk
	nltk.download()

	import nltk
	from nltk.tokenize import RegexpTokenizer

	text = 'Citizens of India are known as Indians.'

	# By passing r'\w+' to the RegexpTokenizer

sdoshi579 / Twitter_sentiment_analysis_using_fastText.py

Last active November 5, 2021 11:11

	import fastText
	import sys
	import os
	import nltk
	nltk.download('punkt')
	import csv
	import datetime
	from bs4 import BeautifulSoup
	import re
	import itertools

sdoshi579 / Digit-recignizer-using-CNN.py

Created March 31, 2019 11:06

Using Keras to implement CNN model which would recognize hand-written digits

	%pylab inline
	import os
	import numpy as np
	import pandas as pd
	from scipy.misc import imread
	from sklearn.metrics import accuracy_score

	import tensorflow as tf
	import keras
	from keras.layers import Dense, Dropout, Flatten

sdoshi579 / Music-classification-into-genres.py

Created April 4, 2019 16:56

Model generated to classify extracted features from music clips into different genres

	import librosa
	import pandas as pd
	import numpy as np
	import matplotlib.pyplot as plt
	%matplotlib inline
	import os
	import csv
	# Preprocessing
	from sklearn.model_selection import train_test_split
	from sklearn.preprocessing import LabelEncoder, StandardScaler

sdoshi579 / Predicting-Traffic-Signs-using-CNN.py

Created September 1, 2019 10:56

Predicting the traffic signs by building CNN model using Keras

	import os
	import pandas as pd
	from scipy.misc import imread
	import math
	import numpy as np
	import cv2
	import keras
	import seaborn as sns
	from keras.layers import Dense, Dropout, Flatten, Input
	from keras.layers import Conv2D, MaxPooling2D

sdoshi579 / Latent_semantic_analysis.py

Created February 26, 2020 04:43

Find the hidden topics represented by the documents using LSA

	import pandas as pd
	from sklearn.feature_extraction.text import TfidfVectorizer
	import nltk
	from sklearn.decomposition import TruncatedSVD
	# If nltk stop word is not downloaded
	# nltk.download('stopwords')
	from nltk.corpus import stopwords

	# List of documents
	a1 = "He is a good dog."