aboutsummaryrefslogtreecommitdiff
path: root/gnqa/paper1_eval/src/run_human_datasets.sh
diff options
context:
space:
mode:
Diffstat (limited to 'gnqa/paper1_eval/src/run_human_datasets.sh')
-rwxr-xr-xgnqa/paper1_eval/src/run_human_datasets.sh63
1 files changed, 63 insertions, 0 deletions
diff --git a/gnqa/paper1_eval/src/run_human_datasets.sh b/gnqa/paper1_eval/src/run_human_datasets.sh
new file mode 100755
index 0000000..6f55d6d
--- /dev/null
+++ b/gnqa/paper1_eval/src/run_human_datasets.sh
@@ -0,0 +1,63 @@
+#!/bin/bash
+
+#echo "Evaluating dataset of questions from domainexperts on the topic of general GN information."
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_domainexpert_general_1.json data/results/human/scores_de_gn_1.json 3
+#sleep 60
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_domainexpert_general_2.json data/results/human/scores_de_gn_2.json 3
+#sleep 60
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_domainexpert_general_3.json data/results/human/scores_de_gn_3.json 3
+#sleep 60
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_domainexpert_general_4.json data/results/human/scores_de_gn_4.json 3
+#sleep 60
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_domainexpert_general_5.json data/results/human/scores_de_gn_5.json 3
+#sleep 60
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_domainexpert_general_6.json data/results/human/scores_de_gn_6.json 3
+#sleep 60
+#echo "Evaluating dataset of questions from domainexpert in the topic of aging"
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_domainexpert_aging_1.json data/results/human/scores_de_aging_1.json 3
+#sleep 60
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_domainexpert_aging_2.json data/results/human/scores_de_aging_2.json 3
+#sleep 60
+#echo "Evaluating dataset of questions from domainexpert in the topic of diabetes"
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_domainexpert_diabetes_1.json data/results/human/scores_de_diabetes_1.json 3
+#sleep 60
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_domainexpert_diabetes_2.json data/results/human/scores_de_diabetes_2.json 3
+#sleep 60
+#echo "Evaluating dataset of questions from citizenscientist in the topic of general"
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_general_1.json data/results/human/scores_cs_gn_1.json 3
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_general_2.json data/results/human/scores_cs_gn_2.json 3
+#sleep 30
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_general_3.json data/results/human/scores_cs_gn_3.json 3
+#sleep 30
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_general_4.json data/results/human/scores_cs_gn_4.json 3
+#sleep 30
+##python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_general_5.json data/results/human/scores_cs_gn_5.json 3
+##sleep 30
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_general_6.json data/results/human/scores_cs_gn_6.json 3
+#sleep 30
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_general_7.json data/results/human/scores_cs_gn_7.json 3
+#echo "Evaluating dataset of questions from citizenscientist in the topic of aging"
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_aging_1.json data/results/human/scores_cs_aging_1.json 3
+#sleep 30
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_aging_2.json data/results/human/scores_cs_aging_2.json 3
+#sleep 30
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_aging_3.json data/results/human/scores_cs_aging_3.json 3
+#sleep 30
+#echo "Evaluating dataset of questions from citizenscientist in the topic of diabetes"
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_diabetes_1.json data/results/human/scores_cs_diabetes_1.json 3
+#sleep 30
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_diabetes_2.json data/results/human/scores_cs_diabetes_2.json 3
+#sleep 30
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_diabetes_3.json data/results/human/scores_cs_diabetes_3.json 3
+#sleep 30
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/human/dataset_citizenscientist_diabetes_4.json data/results/human/scores_cs_diabetes_4.json 3
+#sleep 30
+
+echo "Evaluating dataset of queriestion from citizen scientist on the diabetes topics, generated by gpt4o"
+python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_2.json data/results/gpt4o/scores_cs_gn.json 3
+#sleep 60
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_2.json data/results/gpt4o/scores_cs_diabetes.json 3
+#sleep 60
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_3.json data/results/gpt4o/scores_cs_diabetes.json 3
+#sleep 60
+#python3 ragas_fahamuRAG.py /home/shebes/code/GN-LLM-Hacking/gnqa_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_4.json data/results/gpt4o/scores_cs_diabetes.json 3