Integrated nlpcloud and fixed frontend

raoashish10 · Jan 24, 2023 · 56d4be8 · 56d4be8
1 parent cd8c588
commit 56d4be8
Show file tree

Hide file tree

Showing 60 changed files with 68,645 additions and 1,030 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/Lira/__pycache__/__init__.cpython-310.pyc b/Lira/__pycache__/__init__.cpython-310.pyc
diff --git a/Lira/__pycache__/__init__.cpython-37.pyc b/Lira/__pycache__/__init__.cpython-37.pyc
diff --git a/Lira/__pycache__/__init__.cpython-38.pyc b/Lira/__pycache__/__init__.cpython-38.pyc
diff --git a/Lira/__pycache__/settings.cpython-310.pyc b/Lira/__pycache__/settings.cpython-310.pyc
diff --git a/Lira/__pycache__/settings.cpython-37.pyc b/Lira/__pycache__/settings.cpython-37.pyc
diff --git a/Lira/__pycache__/settings.cpython-38.pyc b/Lira/__pycache__/settings.cpython-38.pyc
diff --git a/Lira/__pycache__/urls.cpython-310.pyc b/Lira/__pycache__/urls.cpython-310.pyc
diff --git a/Lira/__pycache__/urls.cpython-37.pyc b/Lira/__pycache__/urls.cpython-37.pyc
diff --git a/Lira/__pycache__/urls.cpython-38.pyc b/Lira/__pycache__/urls.cpython-38.pyc
diff --git a/Lira/__pycache__/wsgi.cpython-310.pyc b/Lira/__pycache__/wsgi.cpython-310.pyc
diff --git a/Lira/__pycache__/wsgi.cpython-37.pyc b/Lira/__pycache__/wsgi.cpython-37.pyc
diff --git a/Lira/__pycache__/wsgi.cpython-38.pyc b/Lira/__pycache__/wsgi.cpython-38.pyc
diff --git a/Recommender/__pycache__/__init__.cpython-310.pyc b/Recommender/__pycache__/__init__.cpython-310.pyc
diff --git a/Recommender/__pycache__/__init__.cpython-37.pyc b/Recommender/__pycache__/__init__.cpython-37.pyc
diff --git a/Recommender/__pycache__/__init__.cpython-38.pyc b/Recommender/__pycache__/__init__.cpython-38.pyc
diff --git a/Recommender/__pycache__/admin.cpython-310.pyc b/Recommender/__pycache__/admin.cpython-310.pyc
diff --git a/Recommender/__pycache__/admin.cpython-37.pyc b/Recommender/__pycache__/admin.cpython-37.pyc
diff --git a/Recommender/__pycache__/admin.cpython-38.pyc b/Recommender/__pycache__/admin.cpython-38.pyc
diff --git a/Recommender/__pycache__/apps.cpython-310.pyc b/Recommender/__pycache__/apps.cpython-310.pyc
diff --git a/Recommender/__pycache__/apps.cpython-37.pyc b/Recommender/__pycache__/apps.cpython-37.pyc
diff --git a/Recommender/__pycache__/apps.cpython-38.pyc b/Recommender/__pycache__/apps.cpython-38.pyc
diff --git a/Recommender/__pycache__/models.cpython-310.pyc b/Recommender/__pycache__/models.cpython-310.pyc
diff --git a/Recommender/__pycache__/models.cpython-37.pyc b/Recommender/__pycache__/models.cpython-37.pyc
diff --git a/Recommender/__pycache__/models.cpython-38.pyc b/Recommender/__pycache__/models.cpython-38.pyc
diff --git a/Recommender/__pycache__/urls.cpython-310.pyc b/Recommender/__pycache__/urls.cpython-310.pyc
diff --git a/Recommender/__pycache__/urls.cpython-37.pyc b/Recommender/__pycache__/urls.cpython-37.pyc
diff --git a/Recommender/__pycache__/urls.cpython-38.pyc b/Recommender/__pycache__/urls.cpython-38.pyc
diff --git a/Recommender/__pycache__/views.cpython-310.pyc b/Recommender/__pycache__/views.cpython-310.pyc
diff --git a/Recommender/__pycache__/views.cpython-37.pyc b/Recommender/__pycache__/views.cpython-37.pyc
diff --git a/Recommender/__pycache__/views.cpython-38.pyc b/Recommender/__pycache__/views.cpython-38.pyc
diff --git a/Recommender/automated_summary.py b/Recommender/automated_summary.py
@@ -0,0 +1,32 @@
+import pandas as pd
+import nlpcloud
+from nltk.tokenize import sent_tokenize
+import time
+
+data1 = pd.read_csv(r'../data/raw.csv',error_bad_lines=False, engine="python")
+summaries_data = pd.read_csv(r'../data/summaries.csv')
+client = nlpcloud.Client("bart-large-cnn", "f9c60f3620a2bdba081394bd77f44445c2a019b0")
+
+for j in range(68,len(data1)):
+    text = data1['text'].iloc[j]
+    casename = data1['File Name'].iloc[j]
+    texts = sent_tokenize(text)
+    i = 0
+    steps = 40
+    summary_text = ''
+    print(j)
+    print(len(texts))
+    while i < len(texts):
+        print(f"{round(100 * (i / len(texts)),2)}%")
+        if i+steps < len(texts):
+            res = client.summarization(''.join(texts[i:i + steps]))
+            summary_text += res['summary_text'] + ' '
+        else:
+            res = client.summarization(''.join(texts[i:]))
+            summary_text += res['summary_text'] + ' '
+        print("Sleep time")
+        time.sleep(20)
+        i += steps
+    summary_row = summaries_data[summaries_data['File Name'] == casename].head(1).index
+    summaries_data.at[summary_row,'summary'] = summary_text
+    summaries_data.to_csv(r'../data/summaries.csv')
diff --git a/Recommender/legal_stopwords.txt b/Recommender/legal_stopwords.txt
@@ -1,88 +1,88 @@
-Writ
-Witness
-Violation
-Vacate
-Venue
-Transcript
-Trial
-Testimony
-Summons
-Charge
-Sentences
-Respondent
-Prosecutor
-Prosecute
-Petitioner
-Petition
-Party
-Order
-Magistrate
-Motion
-Judge
-Judgment
-Defendant
-AKA
-Accelerated 
-Rehabilitation
-Acknowledgment
-Action
-Adjournment
-Adjudication
-Adjudicatory 
-Court
-Probation
-Affirmation
-Affidavit
-Allegation
-Annulment
-Answer
-Appeal
-Appellant
-Appellee
-Arbitration
-Arrest
-Bail
-Bar
-Brief
-Calendar
-Case
-Conference
-Case 
-File
-Certify
-Challenge
-Charge
-Claim
-Law
-Complaint
-Contract
-Conviction
-Cost
-Count
-Counter 
-Attorney 
-Officer
-Court 
-Trial
-Defendant
-Delinquent
-Deposition
-Discovery
-Dismissal
-Finding
-petitioners
-three
-accused
-evidence
-amendment
-application
-author
-would
-could
-shall
-may
-dated
-years
-passed
-print
-prosecution
+Writ
+Witness
+Violation
+Vacate
+Venue
+Transcript
+Trial
+Testimony
+Summons
+Charge
+Sentences
+Respondent
+Prosecutor
+Prosecute
+Petitioner
+Petition
+Party
+Order
+Magistrate
+Motion
+Judge
+Judgment
+Defendant
+AKA
+Accelerated 
+Rehabilitation
+Acknowledgment
+Action
+Adjournment
+Adjudication
+Adjudicatory 
+Court
+Probation
+Affirmation
+Affidavit
+Allegation
+Annulment
+Answer
+Appeal
+Appellant
+Appellee
+Arbitration
+Arrest
+Bail
+Bar
+Brief
+Calendar
+Case
+Conference
+Case 
+File
+Certify
+Challenge
+Charge
+Claim
+Law
+Complaint
+Contract
+Conviction
+Cost
+Count
+Counter 
+Attorney 
+Officer
+Court 
+Trial
+Defendant
+Delinquent
+Deposition
+Discovery
+Dismissal
+Finding
+petitioners
+three
+accused
+evidence
+amendment
+application
+author
+would
+could
+shall
+may
+dated
+years
+passed
+print
+prosecution
diff --git a/Recommender/migrations/__pycache__/__init__.cpython-310.pyc b/Recommender/migrations/__pycache__/__init__.cpython-310.pyc
diff --git a/Recommender/migrations/__pycache__/__init__.cpython-37.pyc b/Recommender/migrations/__pycache__/__init__.cpython-37.pyc
diff --git a/Recommender/migrations/__pycache__/__init__.cpython-38.pyc b/Recommender/migrations/__pycache__/__init__.cpython-38.pyc
diff --git a/Recommender/summaries.csv b/Recommender/summaries.csv
diff --git a/Recommender/summarizer.py b/Recommender/summarizer.py
@@ -5,7 +5,6 @@
 data = pd.read_csv(r'../data/Mili_bank_forest_final.csv')
 summaries_list = []
 for i in range(len(data)):
-    print(i)
     article_text = str(list(data['text'])[i])
     article_text = re.sub(r'[[0-9]*]', ' ', article_text)
     article_text = re.sub(r'\s+', ' ', article_text)