first commit

Anmol2059 · Sep 2, 2024 · 14e0e6d · 14e0e6d
commit 14e0e6d
Show file tree

Hide file tree

Showing 14 changed files with 152,625 additions and 0 deletions.
diff --git a/chipsal-datasets/datasetInfo.txt b/chipsal-datasets/datasetInfo.txt
@@ -0,0 +1,60 @@
+datasets are from : https://github.com/therealthapa/chipsal24
+---------------------------------------
+Sub Task 1  --> Devnagari Identification
+---------------------------------------
+'Nepali'     : 0
+'Marathi'    : 1
+'Sanskrit'   : 2
+'Bhojpuri'   : 3
+'Hindi'      : 4
+
+[Train Data]
+-------------
+Nepali       : 12544
+Marathi      : 11034
+Sanskrit     : 10996
+Bhojpuri     : 10184
+Hindi        :  7664
+
+[Evaluation Data]
+-----------------
+Nepali       : 2688
+Marathi      : 2364
+Sanskrit     : 2356
+Bhojpuri     : 2182
+Hindi        : 1643
+
+---------------------------------------
+Sub Task 2  --> Hate Speech Detection in Devanagari Script Language
+---------------------------------------
+'non-hate'   : 0
+'hate'       : 1
+
+[Train Data]
+-------------
+non-hate     : 16805
+hate         :  2214
+
+[Evaluation Data]
+-----------------
+non-hate     : 3602
+hate         :  474
+
+---------------------------------------
+Sub Task 3  --> Target Identification for Hate Speech in Devanagari Script Language
+---------------------------------------
+'Individual'     : 0
+'Organization'   : 1
+'Community'      : 2
+
+[Train Data]
+-------------
+Individual       : 1074
+Organization     :  856
+Community        :  284
+
+[Evaluation Data]
+-----------------
+Individual       : 230
+Organization     : 183
+Community        :  61
diff --git a/chipsal-datasets/eval/info.txt b/chipsal-datasets/eval/info.txt
@@ -0,0 +1,60 @@
+datasets are from : https://github.com/therealthapa/chipsal24
+---------------------------------------
+Sub Task 1  --> Devnagari Identification
+---------------------------------------
+'Nepali'     : 0
+'Marathi'    : 1
+'Sanskrit'   : 2
+'Bhojpuri'   : 3
+'Hindi'      : 4
+
+[Train Data]
+-------------
+Nepali       : 12544
+Marathi      : 11034
+Sanskrit     : 10996
+Bhojpuri     : 10184
+Hindi        :  7664
+
+[Evaluation Data]
+-----------------
+Nepali       : 2688
+Marathi      : 2364
+Sanskrit     : 2356
+Bhojpuri     : 2182
+Hindi        : 1643
+
+---------------------------------------
+Sub Task 2  --> Hate Speech Detection in Devanagari Script Language
+---------------------------------------
+'non-hate'   : 0
+'hate'       : 1
+
+[Train Data]
+-------------
+non-hate     : 16805
+hate         :  2214
+
+[Evaluation Data]
+-----------------
+non-hate     : 3602
+hate         :  474
+
+---------------------------------------
+Sub Task 3  --> Target Identification for Hate Speech in Devanagari Script Language
+---------------------------------------
+'Individual'     : 0
+'Organization'   : 1
+'Community'      : 2
+
+[Train Data]
+-------------
+Individual       : 1074
+Organization     :  856
+Community        :  284
+
+[Evaluation Data]
+-----------------
+Individual       : 230
+Organization     : 183
+Community        :  61
diff --git a/chipsal-datasets/eval/run.sh b/chipsal-datasets/eval/run.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+
+# Download task1_index_tweet.csv
+gdown --id 1wmivix0utKHmq6d6ICvpRBTo1pebV3yI -O task1_index_tweet.csv
+
+# Download task1_index_label.csv
+gdown --id 1IicURjnKv8IRvcB99VmSBUIO7SzDfwSu -O task1_index_label.csv
+
+# Download task2_index_tweet.csv
+gdown --id 1SD7bn-5bU0g13GQrZ-RXGDGyAFNSy6VC -O task2_index_tweet.csv
+
+# Download task2_index_label.csv
+gdown --id 1apPJPZnZTke9PJi7z1NvkJKaxn70bCYT -O task2_index_label.csv
+
+# Download task3_index_tweet.csv
+gdown --id 1-2TjS6xPfjWj9YaJGSf-JXXXfNz-2pNT -O task3_index_tweet.csv
+
+# Download task3_index_label.csv
+gdown --id 1-1k1yHOGP7Wij1mUG2iKaSTN8i1WUgPz -O task3_index_label.csv