-
Notifications
You must be signed in to change notification settings - Fork 0
/
DocumentSummary.Rmd
235 lines (191 loc) · 5.72 KB
/
DocumentSummary.Rmd
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
226
227
228
229
230
231
232
233
234
235
---
jupyter:
jupytext:
text_representation:
extension: .Rmd
format_name: rmarkdown
format_version: '1.2'
jupytext_version: 1.11.2
kernelspec:
display_name: Python (py38)
language: python
name: py38
---
```{python}
from gensim.summarization.summarizer import summarize
from gensim.summarization import keywords
import wikipedia
import en_core_web_sm
# Get wiki content.
wikisearch = wikipedia.page("Amitabh Bachchan")
wikicontent = wikisearch.content
nlp = en_core_web_sm.load()
doc = nlp(wikicontent)
# Save the wiki content to a file
# (for reference).
f = open("wikicontent.txt", "w")
f.write(wikicontent)
f.close()
# Summary (0.5% of the original content).
summ_per = summarize(wikicontent, ratio = 0.05)
print("Percent summary")
print(summ_per)
# Summary (200 words)
summ_words = summarize(wikicontent, word_count = 200)
print("Word count summary")
print(summ_words)
```
```{python}
from gensim.summarization import summarize
import requests
from bs4 import BeautifulSoup
```
```{python}
url = 'https://towardsdatascience.com/text-summarization-in-python-76c0a41f0dc4'
page = requests.get(url).text
```
```{python}
soup = BeautifulSoup(page)
```
```{python}
bodies = soup.findAll("div", {"class": "af hx ac dl w x"})
print(bodies)
```
```{python}
print(len(bodies))
```
```{python}
idx = 0
title = bodies[idx].find("h1").text
print(title)
```
```{python}
texts = []
p_tags = bodies[idx].find_all('p')
for p in p_tags:
texts.append(p.text)
article = ' '.join(texts)
```
```{python}
summary = summarize(article, ratio=0.3)
print(summary)
```
```{python}
article = """The current accounting system version has been identified as needing to migrate to a future software:
- Version is on premises, and Sun is moving all future development to Cloud
- Sun Sustainment project in 2018 identified a number of constraints / opportunities and recommend that a version upgrade at minimum.
The scope of this project is to Plan the migration of the accounting system from current sun version to a future software. The deliverable in 2020 will be a migration plan, including the following elements;
- When the migration should occur
- A recommendation as to which software should the migration be to. Note this will probably involve a light system selection project, but should not involve a detailed RFP
- Identify any opportunities to be considered in the migration beyond the core accounting system (i.e. opportunities to not just replace like for like), such as Procurement and CPM/reporting.
- Time effort and money estimates to do the migration
The Migration Plan should be completed by the end of April 2020.
"""
summary = summarize(article, ratio=0.3)
print(summary)
```
```{python}
try:
import docx
except:
# %pip install docx
```
```{python}
import docx
```
```{python}
def get_fileinfo(filename):
time_format = '%Y-%m-%d %H:%M:%S'
try:
file_stats = os.stat(filename)
mod_time = time.strftime(time_format, time.localtime(file_stats[stat.ST_MTIME]))
acc_time = time.strftime(time_format, time.localtime(file_stats[stat.ST_ATIME]))
file_size = file_stats[stat.ST_SIZE]
except Exception as e:
logger.info("ERROR: fileinfo {}".format(e))
mod_time, acc_time, file_size = ["", "", 0]
return mod_time, acc_time, file_size
def scanfiles(folder, filter = None):
for dirpath, _, filenames in os.walk(folder):
for filename in filenames:
filepath = os.path.join(dirpath, filename)
logger.debug(filename)
m_data = None
if filter is not None:
if not isinstance(filter, re.Pattern):
filter = re.compile(filter)
m = re.search(filter, filename)
if not m:
logger.debug("Skipping: {}".format(filename))
continue
m_data = [m.groupdict() for m in filter.finditer(filename)]
try:
mTime, aTime, fSize = get_fileinfo(filepath)
data= {
'folder': dirpath,
'file': filename,
'modified': mTime,
'accessed': aTime,
'size': fSize
}
if m_data:
data['matches'] = m_data
yield data
except Exception as e:
logger.info("ERROR: scan files failed {}".format(e))
```
```{python}
import os
import stat
from datetime import datetime
import logging
import time
import re
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
paths = ['H:', 'IT', 'Budgets', 'Capital', '2020', 'Raw KCP Submissions']
root_path = os.path.join(*paths)
print(root_path)
files = list()
for f in scanfiles(root_path):
files.append(f)
```
```{python}
import pandas as pd
df_files = pd.DataFrame(files)
display(df_files.head())
```
```{python}
import sys
print(sys.version)
print(sys.version_info)
```
```{python}
from openpyxl import load_workbook, Workbook
from openpyxl.utils import column_index_from_string
from openpyxl.styles import PatternFill, Border, Side, Alignment, Protection, Font, Color
def load_WB(path):
# process each sheet...
# assume top row is the titles
# subsequent rows are data...
if os.path.exists(path):
wb = load_workbook(path)
print('Loaded ... {}'.format(path))
else:
print('Creating new workbook...')
wb = Workbook()
try:
wb.save(path)
except:
pass
return wb
```
```{python}
wb_path = 'KCPList.xlsx'
with pd.ExcelWriter(wb_path) as f:
df_files.to_excel(f, sheet_name='files', index=False)
```
```{python}
```
```{python}
```