projectFilter.py

+import pandas as pd
+import argparse
+
+# Filter items by programming language
+# Just need to modify csv_path, result_name, language
+# Just change the parameters here
+parser = argparse.ArgumentParser()
+parser.add_argument('--csv_path', default='0618.csv', type=str)
+parser.add_argument('--sort_values', default='notification count', type=str)
+parser.add_argument('--result_name', default='java_csv.csv', type=str)
+parser.add_argument('--language', default='java', type=str)
+args = parser.parse_args()
+
+
+csv1 = pd.read_csv(args.csv_path)
+
+
+for i in range(len(csv1['project path'])):
+    csv1['project path'][i] = csv1['project path'][i].lower()
+
+
+java_list = []
+for i in range(len(csv1)):
+    if args.language in csv1['project path'][i]:
+        java_list.append(i)
+
+
+java_csv = csv1.loc[java_list]
+java_csv = java_csv.sort_values(args.sort_values, ascending=False)
+java_csv.to_csv(args.result_name, index=False)
\ No newline at end of file

updateRepo_dataAnalysis.py

@@ -37,7 +37,7 @@ for i in range(len(csv2)):
 
 
 for name in in2notin1:
-    csv2.drop(csv2[csv2['project full path'] == name].index, inplace=True)
+    csv2.drop(csv2[csv2['project path'] == name].index, inplace=True)
 
 in1notin2 = []
 for i in range(len(csv1)):
@@ -45,7 +45,7 @@ for i in range(len(csv1)):
         in1notin2.append(csv1.iloc[i, 0])
 
 for name in in1notin2:
-    csv1.drop(csv1[csv1['project full path'] == name].index, inplace=True)
+    csv1.drop(csv1[csv1['project path'] == name].index, inplace=True)
 
 
 for i in range(len(csv1)):