dengemann

# Author: [email protected]
# License: simplified BSD (3 clause)
# Note: code is based on scipy.stats.pearsonr
from scipy import stats

def compute_corr(x, y):
    x = np.asarray(x)
    y = np.asarray(y)
    mx = x.mean(axis=-1)
    my = y.mean(axis=-1)

semihamakinist

"Ecrin"
"Eymen"
"Ceylin"
"Ebrar"
"Tuana"
"Esila"
"Esra"
"Enes"
"Talha"
"Ömer"

cjbayesian

def plot_correlogram(df,figsize=(20,20)):
    ''' Creat an n x n matrix of scatter plots for every
    combination of numeric columns in a dataframe'''

    cols = list(df.columns[df.dtypes=='float64'])
    n = len(cols)
    fig, ax = plt.subplots(n,n,figsize=figsize)
    for i,y in enumerate(cols):
        for j,x in enumerate(cols):
            if i != n-1:

kmike

import numpy as np
import marisa_trie
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.externals import six

class MarisaCountVectorizer(CountVectorizer):

    # ``CountVectorizer.fit`` method calls ``fit_transform`` so
    # ``fit`` is not provided
    def fit_transform(self, raw_documents, y=None):

debasishg

General Background and Overview

1. Probabilistic Data Structures for Web Analytics and Data Mining : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
2. Models and Issues in Data Stream Systems
3. Philippe Flajolet’s contribution to streaming algorithms : A presentation by Jérémie Lumbroso that visits some of the hostorical perspectives and how it all began with Flajolet
4. Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani : One of the early papers on the subject.
5. [Methods for Finding Frequent Items in Data Streams](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&rep=rep1&t

miguelgrinberg

#!flask/bin/python
from flask import Flask, jsonify, abort, request, make_response, url_for
from flask_httpauth import HTTPBasicAuth

app = Flask(__name__, static_url_path = "")
auth = HTTPBasicAuth()

@auth.get_password
def get_password(username):
    if username == 'miguel':

larsmans

#!/usr/bin/python
#
# K-means clustering using Lloyd's algorithm in pure Python.
# Written by Lars Buitinck. This code is in the public domain.
#
# The main program runs the clustering algorithm on a bunch of text documents
# specified as command-line arguments. These documents are first converted to
# sparse vectors, represented as lists of (index, value) pairs.

from collections import defaultdict

larsmans

>>> from pandas import DataFrame
>>> from sklearn.feature_extraction.text import CountVectorizer
>>> docs = ["You can catch more flies with honey than you can with vinegar.",
...         "You can lead a horse to water, but you can't make him drink."]
>>> vect = CountVectorizer(min_df=0., max_df=1.0)
>>> X = vect.fit_transform(docs)
>>> print(DataFrame(X.A, columns=vect.get_feature_names()).to_string())
   but  can  catch  drink  flies  him  honey  horse  lead  make  more  than  to  vinegar  water  with  you
0    0    2      1      0      1    0      1      0     0     0     1     1   0        1      0     2    2
1    1    2      0      1      0    1      0      1     1     1     0     0   1        0      1     0    2

bwhite

"""Information Retrieval metrics

Useful Resources:
http://www.cs.utexas.edu/~mooney/ir-course/slides/Evaluation.ppt
http://www.nii.ac.jp/TechReports/05-014E.pdf
http://www.stanford.edu/class/cs276/handouts/EvaluationNew-handout-6-per.pdf
http://hal.archives-ouvertes.fr/docs/00/72/67/60/PDF/07-busa-fekete.pdf
Learning to Rank for Information Retrieval (Tie-Yan Liu)
"""
import numpy as np

ses4j

def incremental_map_reduce(
		map_f, 
		reduce_f, 
		db, 
		source_table_name, 
		target_table_name, 
		source_queued_date_field_name, 
		counter_table_name = "IncrementalMRCounters", 
		counter_key = None,
		max_datetime = None,