improve verifeied data processing

edenia · Apr 5, 2024 · 9a84704 · 9a84704
1 parent fb8a24d
commit 9a84704
Showing 1 changed file with 3 additions and 3 deletions.
diff --git a/analysis/ethereum_smart_contracts/GPT_verified_data_preprocessing.ipynb b/analysis/ethereum_smart_contracts/GPT_verified_data_preprocessing.ipynb
@@ -44,7 +44,7 @@
     "pretraining_data = pd.read_parquet('/data/forta/ethereum/text/pretraining/raw/verified/verified-smart-contracts.parquet', columns=COLS)\n",
     "# Is anomaly detection?\n",
     "anomaly_detection_training = False\n",
-    "only_evaluation = True"
+    "only_evaluation = False"
    ]
   },
   {
@@ -127,8 +127,8 @@
     "    pretraining_data.loc[pretraining_data['malicious'] == True]['experiment_2_opcodes'].to_csv(\n",
     "        evaluation_file_path, sep=',', index=False)\n",
     "elif not anomaly_detection_training:\n",
-    "    percentaje_normal = number_normal - (number_normal*0.1)\n",
-    "    percentaje_malicious = number_malicious - (number_malicious*0.1)\n",
+    "    percentaje_normal = int(number_normal - (number_normal*0.1))\n",
+    "    percentaje_malicious = int(number_malicious - (number_malicious*0.1))\n",
     "    # Suffle normal and malicious data if no anomaly detection\n",
     "    normal_data = pretraining_data.loc[pretraining_data['malicious'] == False]\n",
     "    malicious_data = pretraining_data.loc[pretraining_data['malicious'] == True]\n",