-
Notifications
You must be signed in to change notification settings - Fork 0
/
part1.py
225 lines (182 loc) · 8.13 KB
/
part1.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
'''
import re
import math
from collections import defaultdict
from nltk.stem import PorterStemmer
# Custom stop words list (simple for the sake of the example)
stop_words = set(["i" ,"me", "my", "myself", "we", "our" ,"ours" ,"ourselves" ,"you" ,"your", "yours" ,"yourself" ,"yourselves", "he" ,"him" ,"his" ,"himself","she", "her", "hers" ,"herself" ,"it" ,"its" ,"itself" ,"they", "them" ,"their" ,"theirs" ,"themselves", "what", "which" ,"who" ,"whom", "this", "that", "these", "those", "am" ,"is", "are" ,"was", "were", "be" ,"been" ,"being" ,"have", "has" ,"had" ,"having", "do" ,"does", "did" ,"doing" ,"a" ,"an" ,"the" ,"and", "but" ,"if" ,"or", "because" ,"as" ,"until" ,"while", "of" ,"at" ,"by", "for" ,"with", "about", "against" ,"between", "into", "through" ,"during", "before", "after" ,"above", "below" ,"to" ,"from" ,"up" ,"down" ,"in" ,"out", "on" ,"off", "over", "under", "again", "further", "then", "once" ,"here", "there", "when", "where", "why" ,"how" ,"all", "any", "both" ,"each" ,"few" ,"more" ,"most", "other" ,"some", "such", "no" ,"nor" ,"not" ,"only", "own" ,"same", "so" ,"than" ,"too", "very", "s" ,"t" ,"can" ,"will", "just", "don" ,"should", "now"])
class ListNode:
def __init__(self, doc_id, tf_idf):
self.doc_id = doc_id
self.tf_idf = tf_idf
self.next = None
self.skip = None
def process_document(document):
# Convert to lowercase
document = document.lower()
# Remove special characters
document = re.sub(r'[^a-z0-9 ]', '', document)
# Remove extra spaces
document = re.sub(r'\s+', ' ', document).strip()
# Tokenize and remove stopwords
tokens = [token for token in document.split() if token not in stop_words]
# Apply stemming
tokens = [stemmer.stem(token) for token in tokens]
return tokens
# Load corpus
with open("input_corpus.txt", 'r') as f:
corpus = [line.strip().split('\t') for line in f.readlines()]
# Initialize stemmer
stemmer = PorterStemmer()
# Build inverted index
inverted_index = defaultdict(list)
for doc_id, document in corpus:
tokens = process_document(document)
doc_length = len(tokens)
token_freqs = defaultdict(int)
for token in tokens:
token_freqs[token] += 1
for token, freq in token_freqs.items():
tf = freq / doc_length
node = ListNode(doc_id, tf)
# Ensure postings are stored in a linked list and ordered by doc_id
if inverted_index[token]:
last_node = inverted_index[token][-1]
last_node.next = node
inverted_index[token].append(node)
else:
inverted_index[token].append(node)
# Calculate IDF and TF-IDF
num_docs = len(corpus)
for token, postings in inverted_index.items():
idf = num_docs / len(postings)
for node in postings:
node.tf_idf *= idf
# Add skip pointers
for token, postings in inverted_index.items():
L = len(postings)
skip_length = round(math.sqrt(L))
if skip_length > 1:
current = postings[0]
count = 0
for i in range(1, L):
count += 1
if count == skip_length:
current.skip = postings[i]
current = current.skip
count = 0
def print_posting_lists(inverted_index):
for term, postings in inverted_index.items():
doc_ids = []
current = postings[0]
while current:
doc_ids.append(current.doc_id)
current = current.next
print(f"{term} -> {', '.join(doc_ids)}")
print_posting_lists(inverted_index)
'''
import re
import math
from collections import defaultdict
from nltk.stem import PorterStemmer
from flask import Flask, request, jsonify
# Custom stop words list
stop_words = set(["i" ,"me", "my", "myself", "we", "our" ,"ours" ,"ourselves" ,"you" ,"your", "yours" ,"yourself" ,"yourselves", "he" ,"him" ,"his" ,"himself","she", "her", "hers" ,"herself" ,"it" ,"its" ,"itself" ,"they", "them" ,"their" ,"theirs" ,"themselves", "what", "which" ,"who" ,"whom", "this", "that", "these", "those", "am" ,"is", "are" ,"was", "were", "be" ,"been" ,"being" ,"have", "has" ,"had" ,"having", "do" ,"does", "did" ,"doing" ,"a" ,"an" ,"the" ,"and", "but" ,"if" ,"or", "because" ,"as" ,"until" ,"while", "of" ,"at" ,"by", "for" ,"with", "about", "against" ,"between", "into", "through" ,"during", "before", "after" ,"above", "below" ,"to" ,"from" ,"up" ,"down" ,"in" ,"out", "on" ,"off", "over", "under", "again", "further", "then", "once" ,"here", "there", "when", "where", "why" ,"how" ,"all", "any", "both" ,"each" ,"few" ,"more" ,"most", "other" ,"some", "such", "no" ,"nor" ,"not" ,"only", "own" ,"same", "so" ,"than" ,"too", "very", "s" ,"t" ,"can" ,"will", "just", "don" ,"should", "now"])
class ListNode:
def __init__(self, doc_id, tf_idf):
self.doc_id = doc_id
self.tf_idf = tf_idf
self.next = None
self.skip = None
def process_document(document):
# Convert to lowercase
document = document.lower()
# Remove special characters
document = re.sub(r'[^a-z0-9 ]', '', document)
# Remove extra spaces
document = re.sub(r'\s+', ' ', document).strip()
# Tokenize and remove stopwords
tokens = [token for token in document.split() if token not in stop_words]
# Apply stemming
tokens = [stemmer.stem(token) for token in tokens]
return tokens
# Load corpus
with open("input_corpus.txt", 'r') as f:
corpus = [line.strip().split('\t') for line in f.readlines()]
# Initialize stemmer
stemmer = PorterStemmer()
# Build inverted index
inverted_index = defaultdict(list)
# ... your inverted index creation code here
for doc_id, document in corpus:
tokens = process_document(document)
doc_length = len(tokens)
token_freqs = defaultdict(int)
for token in tokens:
token_freqs[token] += 1
for token, freq in token_freqs.items():
tf = freq / doc_length
node = ListNode(doc_id, tf)
# Ensure postings are stored in a linked list and ordered by doc_id
if inverted_index[token]:
last_node = inverted_index[token][-1]
last_node.next = node
inverted_index[token].append(node)
else:
inverted_index[token].append(node)
# Calculate IDF and TF-IDF
# ... your IDF and TF-IDF calculation code here
num_docs = len(corpus)
for token, postings in inverted_index.items():
idf = num_docs / len(postings)
for node in postings:
node.tf_idf *= idf
# Add skip pointers
# ... your skip pointers code here
for token, postings in inverted_index.items():
L = len(postings)
skip_length = round(math.sqrt(L))
if skip_length > 1:
current = postings[0]
count = 0
for i in range(1, L):
count += 1
if count == skip_length:
current.skip = postings[i]
current = current.skip
count = 0
def daat_and_query(tokens, inverted_index):
tokens = [stemmer.stem(token) for token in tokens if token not in stop_words]
if not tokens:
return []
sorted_tokens = sorted(tokens, key=lambda x: len(inverted_index.get(x, [])))
if not inverted_index.get(sorted_tokens[0]):
return []
result = set([node.doc_id for node in inverted_index[sorted_tokens[0]]])
for token in sorted_tokens[1:]:
if not inverted_index.get(token):
return []
result &= set([node.doc_id for node in inverted_index[token]])
return sorted(list(result))
def serialize_postings_list(postings):
serialized_postings = []
current = postings[0]
while current:
serialized_postings.append({
"doc_id": current.doc_id,
"tf_idf": current.tf_idf
})
current = current.next
return serialized_postings
def serialize_inverted_index(inverted_index):
serialized_index = {}
for term, postings in inverted_index.items():
serialized_index[term] = serialize_postings_list(postings)
return serialized_index
app = Flask(__name__)
@app.route('/execute_query', methods=['POST'])
def execute_query():
serialized_index = serialize_inverted_index(inverted_index)
return jsonify(serialized_index)
if __name__ == "__main__":
app.run(port=9999)