Reading the json files into the dataframe currently works this way but the file name is the same one for the two different files. Where have I gone wrong?
json_files = glob.glob(r"json_files\*.json")
df = pd.DataFrame()
for _,ele in enumerate(json_files,len(json_files)):
df = pd.concat([df, pd.read_json(ele)])
df['filename'] = os.path.basename(ele).strip(".json")
df = df.drop(['pages'], axis=1)
CodePudding user response:
Or, How about this code?
json_files = glob.glob(r"json_files\*.json")
dfs = []
for _,ele in enumerate(json_files,len(json_files)):
#df = pd.concat([df, pd.read_json(ele)])
df = pd.read_json(ele)
df['filename'] = os.path.basename(ele).strip(".json")
df = df.drop(['pages'], axis=1)
dfs.append(df)
df_final = pd.concat(dfs)