shlomibabluki

# coding=UTF-8
from __future__ import division
import nltk
from collections import Counter

# This is a simple tool for adding automatic hashtags into an article title
# Created by Shlomi Babluki
# Sep, 2013

shlomibabluki

# coding=UTF-8
from __future__ import division
import nltk
import re
import requests

# Add your freebase key here
# If you don't have one, register at https://code.google.com/apis/console
FREEBASE_KEY = ""

shlomibabluki

# coding=UTF-8
from __future__ import division
import nltk
import re
import requests

# Add your freebase key here
# If you don't have one, register at https://code.google.com/apis/console
FREEBASE_KEY = ""

minrk

#!/usr/bin/env python
"""strip outputs from an IPython Notebook

Opens a notebook, strips its output, and writes the outputless version to the original file.

Useful mainly as a git filter or pre-commit hook for users who don't want to track output in VCS.

This does mostly the same thing as the `Clear All Output` command in the notebook UI.

LICENSE: Public Domain

glamp

results = []
for w in ['uniform', 'distance', lambda x: np.log(x)]:
    clf = KNeighborsClassifier(3, weights=w)
    w = str(w)
    clf.fit(train[features], train['high_quality'])
    preds = clf.predict(test[features])
    accuracy = np.where(preds==test['high_quality'], 1, 0).sum() / float(len(test))
    print "Weights: %s, Accuracy: %3f" % (w, accuracy)

    results.append([w, accuracy])

glamp

import pandas as pd
import pylab as pl
from sklearn.neighbors import KNeighborsClassifier


df = pd.read_csv("https://s3.amazonaws.com/demo-datasets/wine.csv")

test_idx = np.random.uniform(0, 1, len(df)) <= 0.3
train = df[test_idx==True]
test = df[test_idx==False]

zacstewart

import os
import numpy
from pandas import DataFrame
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn.cross_validation import KFold
from sklearn.metrics import confusion_matrix, f1_score

NEWLINE = '\n'

shlomibabluki

# coding=UTF-8
from __future__ import division
import re

# This is a naive text summarization algorithm
# Created by Shlomi Babluki
# April, 2013


class SummaryTool(object):

damianavila

"""
Usage: python remove_output.py notebook.ipynb [ > without_output.ipynb ]
Modified from remove_output by Minrk

"""
import sys
import io
import os
from IPython.nbformat.current import read, write

glamp

from dateutil.parser import parse
import pandas as pd

# monthly slaughter records since 1921
df = pd.read_csv("http://bit.ly/119792b")
# parse the data (we could also use pd.to_datetime)
df.date = df.date.apply(parse)
# sort the data frame by date
df = df.sort(['date'])
# create an index