Log processing 2
Task:Each piece of log has indefinite rows, and each row with the same mark indicates that it is a piece of record.
Python
| 1 | import pandas as pd |
| 2 | log_file = 'E://txt//Indefinite _info.txt' |
| 3 | log_info = pd.read_csv(log_file,header=None) |
| 4 | log_g = log_info.groupby(log_info[0].apply(lambda x:x.split("\t")[0]),sort=False) |
| 5 | columns = ["userid","gender","age","salary","province","musicid","watch_time","time"] |
| 6 | df_dic = {} |
| 7 | for c in columns: |
| 8 | df_dic[c]=[] |
| 9 | for index,group in log_g: |
| 10 | rec_dic = {} |
| 11 | rec = group.values.flatten() |
| 12 | rec = '\t'.join(rec).split("\t") |
| 13 | for r in rec: |
| 14 | v = r.split(":") |
| 15 | rec_dic[v[0]]=v[1] |
| 16 | for col in columns: |
| 17 | if col not in rec_dic.keys(): |
| 18 | df_dic[col].append(None) |
| 19 | else: |
| 20 | df_dic[col].append(rec_dic[col]) |
| 21 | df = pd.DataFrame(df_dic) |
| 22 | print(df) |
esProc
| A | ||
| 1 | E://txt//Indefinite _info.txt | |
| 2 | =file(A1).import@s() | |
| 3 | [userid,gender,age,salary,province,musicid,watch_time,time] | |
| 4 | =A2.group@o(_1.array("\t")(1)) | |
| 5 | =A4.(~.(_1.array("\t")).conj().id().align(A3,~.array("\:")(1)).(~.array("\:")(2))).conj() | |
| 6 | =create(${A3.concat@c()}).record(A5) |
The merge grouping of esProc and the special alignment operation make the log processing very easy.
