Working with Data Sources

from sklearn import datasets
iris = datasets.load_iris()
print(len(iris.data))
150
print(len(iris.target))
150
print(iris.target[0]) # Sepal length, Sepal width, Petal length, Petal width
[ 5.1 3.5 1.4 0.2]
print(set(iris.target)) # I. setosa, I. virginica, I. versicolor
{0, 1, 2}

import requests
birthdata_url = 'https://www.umass.edu/statdata/statdata/data/lowbwt.dat'
birth_file = requests.get(birthdata_url)
birth_data = birth_file.text.split('\'r\n') [5:]
birth_header = [x for x in birth_data[0].split( '') if len(x)>=1]
birth_data = [[float(x) for x in y.split( ')'' if len(x)>=1] for y in birth_data[1:] if len(y)>=1]
print(len(birth_data))
189
print(len(birth_data[0]))
11

import requests
housing_url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/housing/housing.data'
housing_header = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV0']
housing_file = requests.get(housing_url)
housing_data = [[float(x) for x in y.split( '') if len(x)>=1] for y in housing_file.text.split('\n') if len(y)>=1]
print(len(housing_data))
506
print(len(housing_data[0]))
14

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/"," one_hot=True)
print(len(mnist.train.images))
55000
print(len(mnist.test.images))
10000
print(len(mnist.validation.images))
5000
print(mnist.train.labels[1,:]) # The first label is a 3'''
[ 0.  0.  0.  1.  0.  0.  0.  0.  0.  0.]

import requests
import io
from zipfile import ZipFile
zip_url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00228/smsspamcollection.zip'
r = requests.get(zip_url)
z = ZipFile(io.BytesIO(r.content))
file = z.read('SMSSpamCollection')
text_data = file.decode()
text_data = text_data.encode('ascii',errors='ignore')
text_data = text_data.decode().split(\n')
text_data = [x.split(\t') for x in text_data if len(x)>=1]
[text_data_target, text_data_train] = [list(x) for x in zip(*text_data)]
print(len(text_data_train))
5574
print(set(text_data_target))
{'ham', 'spam'}
print(text_data_train[1])
Ok lar... Joking wif u oni...

import requests
import io
import tarfile
movie_data_url = 'http://www.cs.cornell.edu/people/pabo/movie-review-data/rt-polaritydata.tar.gz'
r = requests.get(movie_data_url)
# Stream data into temp object
stream_data = io.BytesIO(r.content)
tmp = io.BytesIO()
while True:
    s = stream_data.read(16384)
    if not s:
        break
    tmp.write(s)
stream_data.close()
tmp.seek(0)
# Extract tar file
tar_file = tarfile.open(fileobj=tmp, mode="r:gz")
pos = tar_file.extractfile('rt'-polaritydata/rt-polarity.pos')
neg = tar_file.extractfile('rt'-polaritydata/rt-polarity.neg')
# Save pos/neg reviews (Also deal with encoding)
pos_data = []
for line in pos:
    pos_data.append(line.decode('ISO'-8859-1').encode('ascii',errors='ignore').decode())
neg_data = []
for line in neg:
    neg_data.append(line.decode('ISO'-8859-1').encode('ascii',errors='ignore').decode())
tar_file.close()
print(len(pos_data))
5331
print(len(neg_data))
5331
# Print out first negative review
print(neg_data[0])
simplistic , silly and tedious .

import requests
shakespeare_url = 'http://www.gutenberg.org/cache/epub/100/pg100.txt'
# Get Shakespeare text
response = requests.get(shakespeare_url)
shakespeare_file = response.content
# Decode binary into string
shakespeare_text = shakespeare_file.decode('utf-8')
# Drop first few descriptive paragraphs.
shakespeare_text = shakespeare_text[7675:]
print(len(shakespeare_text)) # Number of characters
5582212

import requests
import io
from zipfile import ZipFile
sentence_url = 'http://www.manythings.org/anki/deu-eng.zip'
r = requests.get(sentence_url)
z = ZipFile(io.BytesIO(r.content))
file = z.read('deu.txt''')
# Format Data
eng_ger_data = file.decode()
eng_ger_data = eng_ger_data.encode('ascii''',errors='ignore''')
eng_ger_data = eng_ger_data.decode().split(\n''')
eng_ger_data = [x.split(\t''') for x in eng_ger_data if len(x)>=1]
[english_sentence, german_sentence] = [list(x) for x in zip(*eng_ger_data)]
print(len(english_sentence))
137673
print(len(german_sentence))
137673
print(eng_ger_data[10])
['I won!, 'Ich habe gewonnen!']