| # this should work - confirm it !! | |
| def get_lists(filename='evaluation3_without\n.txt') | |
| with open(filename, 'r') as outfile: | |
| # filename of the file w/o '\n' | |
| lines = outfile.readlines() | |
| data_list = [eval(lists.strip('\n')) for index, lists in enumerate(lines) if (index+1)%2 == 0] | |
| return data_list |
| import os | |
| import subprocess | |
| import shlex | |
| import time | |
| def convert_doc_to_pdf(ipfile_path, opfile_path): | |
| subprocess.Popen(shlex.split('libreoffice --headless --convert-to pdf "{}" --outdir "{}"'.format(ipfile_path, opfile_path)), stdout=True) |
| # coding: utf-8 | |
| import pickle | |
| import re | |
| from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier | |
| import numpy as np | |
| import pandas as pd | |
| from nltk.tag import pos_tag, pos_tag_sents | |
| from nltk.tokenize import word_tokenize | |
| from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer |
Basic Example is given in the DateFinder.py file itself!
from DateExtractor import DateFinder
df = DateFinder()
# This `find_dates(text)` returns a list of datetime objects taking a string/buffer as a parameter
date_list = df.find_dates('<foobar> (oct 2013 to december 2014) </foobar>')
| http://stackoverflow.com/questions/23322674/how-to-improve-speed-with-stanford-nlp-tagger-and-nltk |
| {% load staticfiles %}<!-- | |
| <script type="text/javascript" src="http://google-maps-utility-library-v3.googlecode.com/svn/trunk/markerwithlabel/src/markerwithlabel.js"></script> --> | |
| <script type="text/javascript"> | |
| function inherits(childCtor, parentCtor) { | |
| /** @constructor */ | |
| function tempCtor() {}; | |
| tempCtor.prototype = parentCtor.prototype; | |
| childCtor.superClass_ = parentCtor.prototype; | |
| childCtor.prototype = new tempCtor(); |
| > Official Google news API - depreciated | |
| Alternative: | |
| - https://newsapi.org/ | |
| - Free to use while not clearly mentioned when the limit is breached | |
| - Mulitple&Huge news sources - can explicit select one of those https://newsapi.org/sources | |
| - Key/Pair auth | |
| - response type: JSON | |
| > Google finance API - depriciated/ Yahoo finance API - depreciated | |
| Alternative: |
| import itertools | |
| import pandas as pd | |
| from pyspark.ml.linalg import Vectors | |
| from pyspark.ml.feature import VectorAssembler | |
| from pyspark.ml import Pipeline | |
| from pyspark.ml.regression import LinearRegression | |
| results = [] | |
| # START ----- VARIABLES | |
| mandatory_columns = set(['Log_Price']) |
| from pyspark.sql.functions import udf | |
| from pyspark.sql.types import * | |
| schema = StructType([ | |
| StructField("foo", FloatType(), False), | |
| StructField("bar", FloatType(), False) | |
| ]) | |
| udf(function(), schema) |
| gcloud dataproc clusters create meow-1434 --bucket shopko-bucket --subnet default --zone asia-east1-b --master-machine-type n1-standard-4 --master-boot-disk-size 100 --num-workers 3 --worker-machine-type n1-standard-4 --worker-boot-disk-size 50 --scopes 'https://www.googleapis.com/auth/cloud-platform' --project affine-dev --initialization-actions 'gs://shopko-bucket/initialisation_script.sh' |