Tomaz Bratanic tomasonjo

## gutenberg_blog_preprocess
# https://www.gutenberg.org/ebooks/95 Prisoner of Zelda

# Fetch the data
target_url = 'https://www.gutenberg.org/files/95/95-0.txt'
import urllib.request
data = urllib.request.urlopen(target_url)
raw_data = data.read().decode('utf8').strip()

# Preprocess text into chapters
import re

## gutenberg_blog_spacy
# Analyze the first chapter
c = chapters[0]
# Get a list of persons
doc=nlp(c)
involved = list(set([ent.text for ent in doc.ents if ent.label_=='PERSON']))
# replace names of involved in the text
# with an id and save the mapping
decode = dict()
for i,x in enumerate(involved):
    # Get mapping

## gutenberg_blog_import
# Get an array of words
ws = c.split()
l = len(ws)

# Iterate through words
for wi,w in enumerate(ws):
    # Skip if the word is not a person
    if not w[:2] == '$$':
        continue
    # Check next x words for any involved person

## fuzzy_search.csv

          
            title
            score

            
              scream
              1.8314404488

            
              a nightmare on elm street: the dream child
              1.3354252577

            
              a nightmare on elm street 4: the dream master
              1.1446502209

            
              bull durham
              1.1446502209

            
              a nightmare on elm street 3: dream warriors
              1.1446502209

## multi-character-wildcard.csv

          
            title
            score

            
              a nightmare on elm street 4: the dream master
              1

            
              a nightmare on elm street: the dream child
              1

            
              my mother dreams the satan's disciples in new york
              1

            
              a nightmare on elm street 3: dream warriors
              1

## single-character-wildcard.csv

          
            title
            score

            
              thx 1138
              1

## logical-operator.csv

          
            title
            score

            
              american psycho
              0.4959547818

            
              bamboozled
              0.4959547818

            
              cast away
              0.4959547818

            
              george washington
              0.4959547818

            
              gladiator
              0.4959547818

## specific_attribute.csv

          
            title
            score

            
              a nightmare on elm street: the dream child
              2.641166687

            
              a nightmare on elm street 4: the dream master
              2.2638571262

            
              a nightmare on elm street 3: dream warriors
              2.2638571262

## range-query.csv

          
            title
            	score

            
              1492: conquest of paradise
              	1.0

            
              15 minutes
              	1.0

            
              2001: a space odyssey
              	1.0

            
              48 hrs.
              	1.0

            
              the fifth element
              	1.0

## boosting-score.csv

          
            title
            	score

            
              a nightmare on elm street 4: the dream master
              	2.463479518890381

            
              a nightmare on elm street 3: dream warriors
              	2.463479518890381

            
              a nightmare on elm street: the dream child
              	1.2535805702209473

            
              1492: conquest of paradise
              	0.1572420448064804

            
              15 minutes
              	0.1572420448064804
	# https://www.gutenberg.org/ebooks/95 Prisoner of Zelda

	# Fetch the data
	target_url = 'https://www.gutenberg.org/files/95/95-0.txt'
	import urllib.request
	data = urllib.request.urlopen(target_url)
	raw_data = data.read().decode('utf8').strip()

	# Preprocess text into chapters
	import re
	# Analyze the first chapter
	c = chapters[0]
	# Get a list of persons
	doc=nlp(c)
	involved = list(set([ent.text for ent in doc.ents if ent.label_=='PERSON']))
	# replace names of involved in the text
	# with an id and save the mapping
	decode = dict()
	for i,x in enumerate(involved):
	# Get mapping
	# Get an array of words
	ws = c.split()
	l = len(ws)

	# Iterate through words
	for wi,w in enumerate(ws):
	# Skip if the word is not a person
	if not w[:2] == '$$':
	continue
	# Check next x words for any involved person
	title	score
	scream	1.8314404488
	a nightmare on elm street: the dream child	1.3354252577
	a nightmare on elm street 4: the dream master	1.1446502209
	bull durham	1.1446502209
	a nightmare on elm street 3: dream warriors	1.1446502209
	title	score
	american psycho	0.4959547818
	bamboozled	0.4959547818
	cast away	0.4959547818
	george washington	0.4959547818
	gladiator	0.4959547818
	title	score
	1492: conquest of paradise	1.0
	15 minutes	1.0
	2001: a space odyssey	1.0
	48 hrs.	1.0
	the fifth element	1.0