bonzanini

# Print most common words in a corpus collected from Twitter
#
# Full description:
# http://marcobonzanini.com/2015/03/02/mining-twitter-data-with-python-part-1/
# http://marcobonzanini.com/2015/03/09/mining-twitter-data-with-python-part-2/
# http://marcobonzanini.com/2015/03/17/mining-twitter-data-with-python-part-3-term-frequencies/
#
# Run:
# python twitter_most_common_words.py <filename.jsonl>

bonzanini

curl -XDELETE http://localhost:9200/blog

curl -XPUT http://localhost:9200/blog -d '{
    "settings" : {
        "index" : {
            "number_of_shards" : 1,
            "number_of_replicas" : 0
        }
    },
    "mapping": {

bonzanini

from nltk import pos_tag
from nltk.tokenize import word_tokenize
from nltk.stem import PorterStemmer, WordNetLemmatizer

stemmer = PorterStemmer()
lemmatiser = WordNetLemmatizer()

print("Stem %s: %s" % ("going", stemmer.stem("going")))
print("Stem %s: %s" % ("gone", stemmer.stem("gone")))
print("Stem %s: %s" % ("goes", stemmer.stem("goes")))

bonzanini

# You need to install scikit-learn:
# sudo pip install scikit-learn
#
# Dataset: Polarity dataset v2.0
# http://www.cs.cornell.edu/people/pabo/movie-review-data/
#
# Full discussion:
# https://marcobonzanini.wordpress.com/2015/01/19/sentiment-analysis-with-python-and-scikit-learn

bonzanini

# run with a custom --n
# python run_luigi.py SquaredNumbers --local-scheduler --n 20

import luigi

class PrintNumbers(luigi.Task):
    n = luigi.IntParameter(default=10)

    def requires(self):
        return []

bonzanini

curl -XDELETE http://localhost:9200/test/articles

curl -XPUT http://localhost:9200/test/_mapping/articles -d '{
    "properties": {
        "content": {
            "type":                "string",
            "position_offset_gap": 100
        }
    }
}'

bonzanini

curl -XPOST http://localhost:9200/test/articles/1 -d '{
    "content": "The quick brown fox"
}'
curl -XPOST http://localhost:9200/test/articles/2 -d '{
    "content": "What does the fox say?"
}'
curl -XPOST http://localhost:9200/test/articles/3 -d '{
    "content": "The quick brown fox jumped over the lazy dog"
}'
curl -XPOST http://localhost:9200/test/articles/4 -d '{

bonzanini

# This code uses Biopython to retrieve lists of articles from pubmed
# you need to install Biopython first.

# If you use Anaconda:
# conda install biopython

# If you use pip/venv:
# pip install biopython

# Full discussion:

bonzanini

consumer_key = 'your-consumer-key'
consumer_secret = 'your-consumer-secret'
access_token = 'your-access-token'
access_secret = 'your-access-secret'