Pandas 按百分比级别对数据帧进行分组
我有一个数据帧：Pandas 按百分比级别对数据帧进行分组,pandas,dataframe,pandas-groupby,quantile,Pandas,Dataframe,Pandas Groupby,Quantile,我有一个数据帧： names = ['OH', 'HL', 'LC', 'OL', 'LH', 'HC'] percentiles = [.75, .90, .95, .98] for col_name in names: for perc in percentiles: k = df[df[col_name] > df[col_name].quantile(perc)] k.loc[:, 'Level'] = str(perc)
names = ['OH', 'HL', 'LC', 'OL', 'LH', 'HC']
percentiles = [.75, .90, .95, .98]
for col_name in names:
for perc in percentiles:
k = df[df[col_name] > df[col_name].quantile(perc)]
k.loc[:, 'Level'] = str(perc)
total_df = pd.concat([total_df, k], sort=False)
print(col_name + ' events:')
print('----------')
print_groups(total_df.groupby('Level'))
Date Open High Low Close Sign Struct Trend OH HL LC OL LH HC
1997-06-17 00:00:00+00:00 812.97 897.60 811.80 894.42 + OLHC U 84.63 85.80 82.62 1.17 85.80 3.18
1998-03-08 00:00:00+00:00 957.59 1055.69 954.24 1055.69 + OLHC U 98.10 101.45 101.45 3.35 101.45 0.00
1998-10-14 00:00:00+00:00 957.28 1066.11 923.32 1005.53 + OLHC U 108.83 142.79 82.21 33.96 142.79 60.58
1998-11-27 00:00:00+00:00 1005.53 1192.97 1000.12 1192.33 + OLHC U 187.44 192.85 192.21 5.41 192.85 0.64
1999-01-10 00:00:00+00:00 1192.33 1278.24 1136.89 1275.09 + OLHC U 85.91 141.35 138.20 55.44 141.35 3.15
1999-04-08 00:00:00+00:00 1271.18 1344.08 1216.03 1343.98 + OLHC U 72.90 128.05 127.95 55.15 128.05 0.10
1999-11-14 00:00:00+00:00 1282.81 1396.12 1233.70 1396.06 + OLHC U 113.31 162.42 162.36 49.11 162.42 0.06
2001-04-25 00:00:00+00:00 1182.91 1253.76 1081.19 1228.75 + OLHC U 70.85 172.57 147.56 101.72 172.57 25.01
2001-12-01 00:00:00+00:00 1066.98 1163.38 1052.83 1137.88 + OLHC U 96.40 110.55 85.05 14.15 110.55 25.50
2003-03-30 00:00:00+00:00 836.25 895.78 788.90 863.50 + OLHC U 59.53 106.88 74.60 47.35 106.88 32.28
2003-05-13 00:00:00+00:00 863.50 947.51 843.68 942.30 + OLHC U 84.01 103.83 98.62 19.82 103.83 5.21
2003-09-22 00:00:00+00:00 977.59 1040.18 974.21 1022.82 + OLHC U 62.59 65.97 48.61 3.38 65.97 17.36
2003-11-05 00:00:00+00:00 1022.82 1061.44 990.34 1051.81 + OLHC U 38.62 71.10 61.47 32.48 71.10 9.63
2003-12-19 00:00:00+00:00 1053.14 1091.03 1031.24 1088.67 + OLHC U 37.89 59.79 57.43 21.90 59.79 2.36
2004-12-05 00:00:00+00:00 1095.74 1197.11 1090.23 1191.17 + OLHC U 101.37 106.88 100.94 5.51 106.88 5.94
2005-01-18 00:00:00+00:00 1190.84 1217.90 1173.76 1195.98 + OLHC U 27.06 44.14 22.22 17.08 44.14 21.92
2005-05-30 00:00:00+00:00 1142.40 1199.56 1136.22 1198.78 + OLHC U 57.16 63.34 62.56 6.18 63.34 0.78
2006-02-18 00:00:00+00:00 1274.61 1294.90 1253.61 1287.24 + OLHC U 20.29 41.29 33.63 21.00 41.29 7.66
2006-04-03 00:00:00+00:00 1287.14 1310.88 1268.42 1297.81 + OLHC U 23.74 42.46 29.39 18.72 42.46 13.07
2006-09-26 00:00:00+00:00 1267.60 1336.60 1266.67 1336.34 + OLHC U 69.00 69.93 69.67 0.93 69.93 0.26
2006-11-09 00:00:00+00:00 1335.37 1389.45 1327.10 1378.33 + OLHC U 54.08 62.35 51.23 8.27 62.35 11.12
2006-12-23 00:00:00+00:00 1378.35 1431.81 1375.60 1410.76 + OLHC U 53.46 56.21 35.16 2.75 56.21 21.05
2007-09-13 00:00:00+00:00 1455.27 1503.41 1370.60 1483.95 + OLHC U 48.14 132.81 113.35 84.67 132.81 19.46
2008-04-20 00:00:00+00:00 1293.37 1395.90 1256.98 1390.33 + OLHC U 102.53 138.92 133.35 36.39 138.92 5.57
2009-04-07 00:00:00+00:00 770.05 845.61 666.79 815.55 + OLHC U 75.56 178.82 148.76 103.26 178.82 30.06
2009-05-21 00:00:00+00:00 815.55 930.17 814.84 888.33 + OLHC U 114.62 115.33 73.49 0.71 115.33 41.84
2009-07-04 00:00:00+00:00 888.33 956.23 881.46 896.42 + OLHC U 67.90 74.77 14.96 6.87 74.77 59.81
2009-08-17 00:00:00+00:00 896.42 1018.00 869.32 979.73 + OLHC U 121.58 148.68 110.41 27.10 148.68 38.27
2009-09-30 00:00:00+00:00 979.73 1080.15 979.73 1057.08 + OLHC U 100.42 100.42 77.35 0.00 100.42 23.07
2009-11-13 00:00:00+00:00 1057.08 1105.37 1020.18 1093.48 + OLHC U 48.29 85.19 73.30 36.90 85.19 11.89
2010-10-31 00:00:00+00:00 1126.57 1196.14 1122.79 1183.26 + OLHC U 69.57 73.35 60.47 3.78 73.35 12.88
2010-12-14 00:00:00+00:00 1185.71 1246.73 1173.00 1241.59 + OLHC U 61.02 73.73 68.59 12.71 73.73 5.14
2011-01-27 00:00:00+00:00 1241.58 1301.29 1232.85 1299.54 + OLHC U 59.71 68.44 66.69 8.73 68.44 1.75
2011-03-12 00:00:00+00:00 1299.63 1344.07 1275.10 1304.28 + OLHC U 44.44 68.97 29.18 24.53 68.97 39.79
2011-12-01 00:00:00+00:00 1223.46 1292.66 1158.66 1244.58 + OLHC U 69.20 134.00 85.92 64.80 134.00 48.08
2012-01-14 00:00:00+00:00 1246.03 1296.82 1202.37 1289.09 + OLHC U 50.79 94.45 86.72 43.66 94.45 7.73
2012-02-27 00:00:00+00:00 1290.22 1371.94 1290.22 1367.59 + OLHC U 81.72 81.72 77.37 0.00 81.72 4.35
2012-07-08 00:00:00+00:00 1318.90 1374.81 1266.74 1354.68 + OLHC U 55.91 108.07 87.94 52.16 108.07 20.13
2012-08-21 00:00:00+00:00 1354.66 1426.68 1325.41 1413.17 + OLHC U 72.02 101.27 87.76 29.25 101.27 13.51
2012-12-31 00:00:00+00:00 1366.42 1448.00 1366.42 1426.19 + OLHC U 81.58 81.58 59.77 0.00 81.58 21.81
2013-02-13 00:00:00+00:00 1426.19 1524.69 1426.19 1520.33 + OLHC U 98.50 98.50 94.14 0.00 98.50 4.36
names = ['OH', 'HL', 'LC', 'OL', 'LH', 'HC']
percentiles = [.75, .90, .95, .98]
for col_name in names:
for perc in percentiles:
k = df[df[col_name] > df[col_name].quantile(perc)]
k.loc[:, 'Level'] = str(perc)
total_df = pd.concat([total_df, k], sort=False)
print(col_name + ' events:')
print('----------')
print_groups(total_df.groupby('Level'))
col_name = 'HC'
group_name = col_name + '_lev'
level_value = .95
hc_group = df[df[col_name] > df[col_name].quantile(level_value)]
hc_group.loc[:, group_name] = col_name
names = ['OH', 'HL', 'LC', 'OL', 'LH', 'HC']
percentiles = [.75, .90, .95, .98]
for col_name in names:
for perc in percentiles:
k = df[df[col_name] > df[col_name].quantile(perc)]
k.loc[:, 'Level'] = str(perc)
total_df = pd.concat([total_df, k], sort=False)
print(col_name + ' events:')
print('----------')
print_groups(total_df.groupby('Level'))
Date Open High Low Close Sign Struct Trend OH HL LC OL LH HC HC_lev
1998-10-14 00:00:00+00:00 957.28 1066.11 923.32 1005.53 + OLHC U 108.83 142.79 82.21 33.96 142.79 60.58 HC
2009-05-21 00:00:00+00:00 815.55 930.17 814.84 888.33 + OLHC U 114.62 115.33 73.49 0.71 115.33 41.84 HC
2009-07-04 00:00:00+00:00 888.33 956.23 881.46 896.42 + OLHC U 67.90 74.77 14.96 6.87 74.77 59.81 HC
2009-08-17 00:00:00+00:00 896.42 1018.00 869.32 979.73 + OLHC U 121.58 148.68 110.41 27.10 148.68 38.27 HC
2011-03-12 00:00:00+00:00 1299.63 1344.07 1275.10 1304.28 + OLHC U 44.44 68.97 29.18 24.53 68.97 39.79 HC
2011-12-01 00:00:00+00:00 1223.46 1292.66 1158.66 1244.58 + OLHC U 69.20 134.00 85.92 64.80 134.00 48.08 HC
2016-06-29 00:00:00+00:00 2065.04 2120.55 1991.68 2070.77 + OLHC U 55.51 128.87 79.09 73.36 128.87 49.78 HC
names = ['OH', 'HL', 'LC', 'OL', 'LH', 'HC']
percentiles = [.75, .90, .95, .98]
for col_name in names:
for perc in percentiles:
k = df[df[col_name] > df[col_name].quantile(perc)]
k.loc[:, 'Level'] = str(perc)
total_df = pd.concat([total_df, k], sort=False)
print(col_name + ' events:')
print('----------')
print_groups(total_df.groupby('Level'))
names = ['OH', 'HL', 'LC', 'OL', 'LH', 'HC']
percentiles = [.75, .90, .95, .98]
for col_name in names:
for perc in percentiles:
k = df[df[col_name] > df[col_name].quantile(perc)]
k.loc[:, 'Level'] = str(perc)
total_df = pd.concat([total_df, k], sort=False)
print(col_name + ' events:')
print('----------')
print_groups(total_df.groupby('Level'))
names = ['OH', 'HL', 'LC', 'OL', 'LH', 'HC']
percentiles = [.75, .90, .95, .98]
for col_name in names:
for perc in percentiles:
k = df[df[col_name] > df[col_name].quantile(perc)]
k.loc[:, 'Level'] = str(perc)
total_df = pd.concat([total_df, k], sort=False)
print(col_name + ' events:')
print('----------')
print_groups(total_df.groupby('Level'))
names = ['OH', 'HL', 'LC', 'OL', 'LH', 'HC']
percentiles = [.75, .90, .95, .98]
for col_name in names:
for perc in percentiles:
k = df[df[col_name] > df[col_name].quantile(perc)]
k.loc[:, 'Level'] = str(perc)
total_df = pd.concat([total_df, k], sort=False)
print(col_name + ' events:')
print('----------')
print_groups(total_df.groupby('Level'))
你能告诉我怎么处理这个问题吗？最后，我找到了解决办法。也许它对其他人有用
names = ['OH', 'HL', 'LC', 'OL', 'LH', 'HC']
percentiles = [.75, .90, .95, .98]
for col_name in names:
for perc in percentiles:
k = df[df[col_name] > df[col_name].quantile(perc)]
k.loc[:, 'Level'] = str(perc)
total_df = pd.concat([total_df, k], sort=False)
print(col_name + ' events:')
print('----------')
print_groups(total_df.groupby('Level'))