aneesha

aneesha

aneesha

from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.datasets import fetch_20newsgroups
from sklearn.decomposition import NMF, LatentDirichletAllocation

def display_topics(model, feature_names, no_top_words):
    for topic_idx, topic in enumerate(model.components_):
        print "Topic %d:" % (topic_idx)
        print " ".join([feature_names[i]
                        for i in topic.argsort()[:-no_top_words - 1:-1]])

aneesha

'''
Merge/combine courses in the OpenedX OLX format.
'''

import sys
import os
from distutils.dir_util import copy_tree
import json

# Example:

aneesha

function [W] = NNDEIG(A,k,flag);
%
% This function implements the NNDSVD algorithm described in [1] for
% initialization of Nonnegative Matrix Factorization Algorithms
% for symmetric NMF so uses Eigendecomposition
%
% [W] = nndeig(A,k,flag);
%
% INPUT
% ------------

aneesha

from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.datasets import fetch_20newsgroups
from sklearn.decomposition import NMF, LatentDirichletAllocation
import numpy as np

def display_topics(H, W, feature_names, documents, no_top_words, no_top_documents):
    for topic_idx, topic in enumerate(H):
        print "Topic %d:" % (topic_idx)
        print " ".join([feature_names[i]
                        for i in topic.argsort()[:-no_top_words - 1:-1]])

aneesha

from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.decomposition import NMF, LatentDirichletAllocation
import numpy as np

def display_topics(H, W, feature_names, documents, no_top_words, no_top_documents):
    for topic_idx, topic in enumerate(H):
        print "Topic %d:" % (topic_idx)
        print " ".join([feature_names[i]
                        for i in topic.argsort()[:-no_top_words - 1:-1]])
        top_doc_indices = np.argsort( W[:,topic_idx] )[::-1][0:no_top_documents]

aneesha

import dask.dataframe as dd

df = dd.read_csv('logs/2018-*.*.csv', parse_dates=['timestamp'])
df.groupby(df.timestamp.dt.hour).value.mean().compute()

aneesha

import h5py
f = h5py.File('myhdf5file.hdf5')
dset = f['/data/path']

import dask.array as da
x = da.from_array(dset, chunks=(5000, 5000))

aneesha