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
from numpy import array | |
from numpy import asarray | |
from numpy import zeros | |
from keras.preprocessing.text import Tokenizer | |
from keras.preprocessing.sequence import pad_sequences | |
from keras.models import Sequential | |
from keras.layers import Dense | |
from keras.layers import Flatten | |
from keras.layers import Embedding | |
# define documents |
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
#Term Frequency | |
def termfreq(document, word): | |
N = len(document) | |
occurance = len([token for token in document if token == word]) | |
return occurance/N | |
#Inverse Document Frequency | |
def inverse_doc_freq(word): | |
try: |
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
from math import exp | |
from random import seed | |
from random import random | |
# Initialize a network | |
def initialize_network(n_inputs, n_hidden, n_outputs): | |
network = list() | |
hidden_layer = [{'weights':[random() for i in range(n_inputs + 1)]} for i in range(n_hidden)] | |
network.append(hidden_layer) | |
output_layer = [{'weights':[random() for i in range(n_hidden + 1)]} for i in range(n_outputs)] |
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
# Make a prediction with weights | |
def predict(row, weights): | |
activation = weights[0] | |
for i in range(len(row)-1): | |
activation += weights[i + 1] * row[i] | |
return 1.0 if activation >= 0.0 else 0.0 | |
# Estimate Perceptron weights using stochastic gradient descent | |
def train_weights(train, l_rate, n_epoch): |
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
# Example of making predictions | |
from math import sqrt | |
# calculate the Euclidean distance between two vectors | |
def euclidean_distance(row1, row2): | |
distance = 0.0 | |
for i in range(len(row1)-1): | |
distance += (row1[i] - row2[i])**2 | |
return sqrt(distance) |
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
# Make a prediction with coefficients | |
def predict(row, coefficients): | |
yhat = coefficients[0] | |
for i in range(len(row)-1): | |
yhat += coefficients[i + 1] * row[i] | |
return yhat | |
# Estimate linear regression coefficients using stochastic gradient descent | |
def coefficients_sgd(train, l_rate, n_epoch): | |
coef = [0.0 for i in range(len(train[0]))] |
We can make this file beautiful and searchable if this error is corrected: No tabs found in this TSV file in line 0.
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
artist | |
jr. | |
stills & nash | |
the creator | |
wind & fire | |
!!! | |
10cc | |
112 | |
12 stones | |
2 chainz |
We can't make this file beautiful and searchable because it's too large.
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
0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 | |
0.3477159 -0.10670821 0.45994064 -0.34369546 -0.122856915 -0.7744754 0.19030279 0.05720891 0.1698621 -0.169827 -0.40953735 -0.23523934 0.048396867 0.7052571 0.34191108 -0.049767286 0.21731612 -0.64538217 -0.23329686 0.34425774 0.051952425 -0.4196746 -0.17587171 0.55343366 0.35680598 -0.16747452 -0.87103546 -0.030037874 -0.7526807 0.40080637 -0.22336994 0.021601401 -0.20519453 -0.60855657 0.32687736 0.27665842 -0.16321175 -0.5943156 0.31605804 -0.4849278 -0.039805546 -0.5149964 0.5394806 0.12340542 -0.29706863 -0.21343571 -0.17491385 0.25965297 -0.061519373 -0.1642966 -0.53483236 -0.8100034 0.01949798 0.11995843 0.003958153 -0.27783373 0.13840675 -0.23143578 0.3111198 -0.19826624 -0.05331649 0.42159384 0.04027778 0.24033114 0 |
We can make this file beautiful and searchable if this error is corrected: No tabs found in this TSV file in line 0.
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
joe echo | |
crowded house | |
paul mccartney | |
joshua radin | |
the len price 3 | |
noah and the whale | |
pearl jam | |
bruce springsteen | |
miles kane | |
tom petty |
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
Time Commitment: 50 hours, Nov 23- Nov 30 ‘2018 | |
Create baseline model with python: | |
* Graph theory with python | |
* Poster representation | |
* Search-Even Misspelled words | |
* Multiple movies attributes- Persona and Word Cloud | |
* Filter of Genre, IMDB rating, Popularity and actor | |
* Comments and Screenshot capability- Login | |
* Hosting with a Virtual Machine |
NewerOlder