-
Notifications
You must be signed in to change notification settings - Fork 0
/
main.py
141 lines (115 loc) · 3.75 KB
/
main.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
from tkinter import *
from vsm import *
import timeit
import os
results = []
query = None
stop_words = stopWordList("Stopword-List.txt")
docs_tokens = documentTokenizer(30, stop_words)
extract_documents = get_document_extracts(30)
inverted_index = invertedIndex(docs_tokens)
doc_vectors =documnetVector(docs_tokens,inverted_index)
def clicked():
start_time = timeit.default_timer()
global query
global results
query = searchQuery.get()
searchQuery.delete(0, END)
# query = "cricket politics"
query_tokens = queryProcessing(query, stop_words)
query_vector = queryVector(query,stop_words,inverted_index)
results = cosineSimalirity(doc_vectors,query_vector,query_tokens)
# results = sorted(results.items(), key=lambda x: x[1], reverse=True)
# for doc_id, score in results:
# print(f"Document {doc_id}: (score={score:.4f})")
searchStats.config(
text=f'Processed {(docs_tokens.count)} documents in {len(inverted_index.keys())}ms , fetched {len(results)} results')
for label in scrollable_frame.winfo_children():
label.destroy()
for i, (doc_id, score) in enumerate(results):
try:
if score ==0:
continue
label_text = f"Document {doc_id}: extract \"{extract_documents[int(doc_id)-1]}\" (score={score:.4f})"
label = Label(scrollable_frame, text=label_text,
anchor="w", wraplength=450)
label.pack(pady=5, padx=10)
label.bind("<Button-1>", lambda event,
index=int(doc_id)-1: open_file(index))
except ValueError:
pass
end_time = timeit.default_timer()
execution_time_in_microseconds = (end_time - start_time) * 1_000_000
searchStats.config(text=f'Search result for {query} \nProcessed in {execution_time_in_microseconds} ms , fetched {len([val for _, val in results if val != 0])} results')
def open_file(index):
# set the exact path of the folder dataset
file_name = f"E:/study/IR/IR assignment 2/Dataset/{index+1}.txt"
os.startfile(file_name)
window = Tk()
window.title("VSM")
window.geometry('500x500')
window.resizable(False, False)
window.configure(bg="#f5f5f5")
exampleHeading = Label(
window,
text="Write your query like \"cricket politics\"",
font=("Arial", 8),
fg="#333",
bg="#f5f5f5"
)
exampleHeading.grid(column=0, row=0, columnspan=2, pady=10, padx=100)
header_label = Label(
window,
text="Search Here",
font=("Arial Bold", 20),
fg="#333",
bg="#f5f5f5"
)
header_label.grid(column=0, row=1)
searchQuery = Entry(
window,
width=50,
font=("Arial", 10),
bd=0,
bg="#f9f9f9",
highlightcolor="#333",
highlightthickness=1,
highlightbackground="#ccc"
)
searchQuery.grid(column=0, row=2, padx=100)
searchStats = Label(
window,
text="Welcome",
font=("Arial Bold", 8),
fg="#333",
bg="#f5f5f5"
)
searchStats.grid(column=0, row=3)
searchBtn = Button(
window,
text="Search",
font=("Arial Bold", 14),
bg="#333",
fg="#fff",
bd=0,
activebackground="#555",
activeforeground="#fff",
command=clicked
)
searchBtn.grid(column=0, row=4, padx=100, pady=10)
canvas = Canvas(window, width=500, height=400, bg="#fff")
scrollbar = Scrollbar(window, orient=VERTICAL, command=canvas.yview)
scrollable_frame = Frame(canvas, bg="#fff")
scrollable_frame.bind(
"<Configure>",
lambda e: canvas.configure(
scrollregion=canvas.bbox("all")
)
)
canvas.create_window((0, 0), window=scrollable_frame, anchor="nw")
canvas.configure(yscrollcommand=scrollbar.set)
canvas.grid(column=0, row=5, sticky="nsew")
scrollbar.grid(column=1, row=5, sticky="ns")
window.grid_columnconfigure(0, weight=1)
window.grid_rowconfigure(5, weight=1)
window.mainloop()