import pandas as pd
from textblob import Word
headers = pd.read_csv("header.csv")
headers['Header']
0 GPRPy
1 Simplemost installation
2 Running the software
3 Running automatically generated scripts
4 In case of trouble
5 Uninstalling GPRPy
6 News
7 Scale-recurrent Network for Deep Image Deblur...
8 Our results on real data
9 Results on the testing dataset
10 More cases on real photos from previous papers:
11 Prerequisites
12 Installation
13 Testing
14 Evaluation
15 Training
16 Models
17 How to choose
18 Reference
19 Contact
20 Reference
21 connect to the API
22 download single scene by known product id
23 search by polygon, time, and Hub query keywords
24 download all results from the search
25 GeoJSON FeatureCollection containing footprin...
26 GeoPandas GeoDataFrame with the metadata of t...
27 Get basic information about the product: its ...
28 its download url
29 Get the product's full metadata available on ...
...
831 Local config
832 Example of a json file
833 Example of a js module
834 Custom renderers
835 Known plugins
836 pyGeoPressure -->
837 Features
838 Getting Started
839 Installation
840 Example
841 Pore Pressure Prediction using well log data
842 Documentation
843 Contribute
844 Report Bugs
845 Suggest Enhancements
846 Submit Pull Requests
847 Support
848 License
849 News!
850 Contents
851 Introduction
852 Requirements
853 Quick Start
854 Training
855 Evaluation
856 Prediction
857 Baseline
858 Contributors
859 Citation
860 License
Name: Header, Length: 861, dtype: object
citation = [Word("citation").synsets[2], Word("reference").synsets[1], Word("cite").synsets[3]]
run = [Word("run").synsets[9],Word("run").synsets[34],Word("execute").synsets[4]]
install = [Word("installation").synsets[0],Word("install").synsets[0],Word("setup").synsets[1],Word("prepare").synsets[0],Word("preparation").synsets[0],Word("manual").synsets[0],Word("guide").synsets[2],Word("guide").synsets[9]]
download = [Word("download").synsets[0]]
requirement = [Word("requirement").synsets[2],Word("prerequisite").synsets[0],Word("prerequisite").synsets[1],Word("dependency").synsets[0],Word("dependent").synsets[0]]
contact = [Word("contact").synsets[9]]
description = [Word("description").synsets[0],Word("description").synsets[1],Word("introduction").synsets[3],Word("introduction").synsets[6],Word("basics").synsets[0],Word("initiation").synsets[1],Word("start").synsets[0],Word("start").synsets[4],Word("started").synsets[0],Word("started").synsets[1],Word("started").synsets[7],Word("started").synsets[8],Word("overview").synsets[0],Word("summary").synsets[0],Word("summary").synsets[2]]
contributor = [Word("contributor").synsets[0]]
documentation = [Word("documentation").synsets[1]]
license = [Word("license").synsets[3],Word("license").synsets[0]]
usage = [Word("usage").synsets[0],Word("example").synsets[0],Word("example").synsets[5],Word("implement").synsets[1],Word("implementation").synsets[1],Word("demo").synsets[1],Word("tutorial").synsets[0],Word("tutorial").synsets[1]]
update = [Word("updating").synsets[0],Word("updating").synsets[3]]
issues = [Word("issues").synsets[0],Word("errors").synsets[5],Word("problems").synsets[0],Word("problems").synsets[2]]
support = [Word("support").synsets[7],Word("help").synsets[0],Word("help").synsets[9],Word("report").synsets[0],Word("report").synsets[6]]
group = dict()
group.update({"citation":citation})
group.update({"download":download})
group.update({"run":run})
group.update({"installation":install})
group.update({"requirement":requirement})
group.update({"contact":contact})
group.update({"description":description})
group.update({"contributor":contributor})
group.update({"documentation":documentation})
group.update({"license":license})
group.update({"usage":usage})
group.update({"update":update})
group.update({"issues":issues})
group.update({"support":support})
def find_sim(wordlist,wd): #returns the max probability between a word and subgroup
simvalue = []
for sense in wordlist:
if(wd.path_similarity(sense)!=None):
simvalue.append(wd.path_similarity(sense))
if(len(simvalue)!=0):
return max(simvalue)
else:
return 0
def match_group(word_syn,group,threshold):
currmax = 0
maxgroup = ""
simvalues = dict()
for sense in word_syn: #for a given sense of a word
similarities = []
for key, value in group.items(): #value has all the similar words
path_sim = find_sim(value,sense)
# print("Similarity is:",path_sim)
if(path_sim>threshold): #then append to the list
if(path_sim>currmax):
maxgroup = key
currmax = path_sim
return maxgroup
datadf = pd.DataFrame({'Header': [], 'Group': []})
matchedgroups = []
for h in headers["Header"]:
sentence = h.split(" ")[1:]
for s in sentence:
synn = Word(s).synsets
if(len(synn)>0):
bestgroup = match_group(synn,group,0.6)
if(bestgroup!=""):
datadf = datadf.append({'Header' : h, 'Group' : bestgroup}, ignore_index=True)
print(datadf)
datadf.to_csv('header_groups.csv', index=False)
Header Group 0 Simplemost installation installation 1 Running the software run 2 Running automatically generated scripts run 3 In case of trouble issues 4 Prerequisites requirement 5 Installation installation 6 Reference citation 7 Contact contact 8 Reference citation 9 download single scene by known product id download 10 download all results from the search download 11 Get basic information about the product: its ... description 12 its download url download 13 Get the product's full metadata available on ... description 14 Introduction description 15 Prepare training data installation 16 Begin to train description 17 Quick start description 18 Citation citation 19 a record schema. We can get initial values f... description 20 coordinate reference system as the source. Th... citation 21 Get a point on the boundary of the record's description 22 executes ``dst.flush(); dst.close()``. run 23 Requirements requirement 24 Installation installation 25 Linux Setup with virtualenv installation 26 Install TensorFlow installation 27 Windows Setup with python 3 and Anaconda installation 28 if you need to get chumpy description 29 Demo usage .. ... ... 344 License license 345 Introduction description 346 Documentation documentation 347 Issues issues 348 License license 349 Installation installation 350 Documentation documentation 351 License license 352 Get the 1st bending mode shape. Results are ... description 353 to avoid getting the "Factor is exactly singu... description 354 to avoid getting the "Factor is exactly singu... issues 355 Install or Update installation 356 Install or Update update 357 Usage usage 358 Example of a json file usage 359 Example of a js module usage 360 Getting Started description 361 Getting Started description 362 Installation installation 363 Example usage 364 Documentation documentation 365 Report Bugs support 366 Support support 367 License license 368 Introduction description 369 Requirements requirement 370 Quick Start description 371 Contributors contributor 372 Citation citation 373 License license [374 rows x 2 columns]