Python CSV：用新值替换行的单元格值（浮点数）（float）

时间：2017-08-22 01:58:39

标签： python python-3.x pandas csv

已更新示例CSV数据：

c1,c2,v1,v2,p1,p2,r1,a1,f1,f2,f3,Time_Stamp 

0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:00
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:01
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:02
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:03
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:04
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:05
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:06
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:07
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:08
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:09
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:10
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:11
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:12
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:13
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:14
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:15
415.7,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,13/06/2017 16:38:16 
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:17
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:18
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:19
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:20
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:21
415.7,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,13/06/2017 16:38:22
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:23
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:24
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:25
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:26
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:27
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:28
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:29
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:30
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:31
415.7,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,13/06/2017 16:38:32
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:33
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:34
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:35
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:36

已编辑 - 阅读CSV，Python代码：

import numpy as np
from datetime import date,time,datetime
import pandas as pd

def readcsv(x): #def function to read csv files based on input below
    Data = pd.read_csv(x, parse_dates=['Time_Stamp'], infer_datetime_format=True)
    Data['Date'] = Data.Time_Stamp.dt.date #creating Date Column in the Data Frame ( does not affect the main .csv file)
    Data['Time'] = Data.Time_Stamp.dt.time #creating Time Column in the Data Frame ( also does not affect the main .csv file)
    #print (Data) #<-- prints the output
    #print (Data['Time_Stamp'][6000:7000]) <- print from row 6000 to 7000 of the data frame (has over 150'000 rows)
    Data['Time_Stamp'] = pd.to_datetime(Data['Time_Stamp']) # Time_Stamp Data Frame
    print(Data[1:6])
    return Data

Data = readcsv('data.csv')


#Data = csv file data 

def getMask(start,end,Data):
    mask = (Data['Time_Stamp'] > start) & (Data['Time_Stamp'] <= end)
    return mask;

start = '2017-06-13 16:00:00'
end = '2017-06-13 16:40:00'
timerange = Data.loc[getMask(start, end, Data)]

pspike = timerange.loc[timerange['c1'] <= 5.0]

pspike输出：

行 ：例如 - ＆GT;打印pspike后，打印的行的time值为16:38:15，下一个打印的行的time值为16:38:17，这意味着它跳过一行时间值为16:38:16

[例如下面] 

13/06/2017 16:38:12
13/06/2017 16:38:13
13/06/2017 16:38:14
13/06/2017 16:38:15
13/06/2017 16:38:17
13/06/2017 16:38:18

运行下面的代码后，它会打印出跳过的行（仅限Time_Stamp值），其time值为16:38:16，16:38:22和16:38:32根据{{​​1}}

的输出跳过具有该值的行 
pspike

输出：

for i in range(timerange.shape[0] - 1):
row1 = timerange.iloc[i]
row2 = timerange.iloc[i+1]
if (row2[-1] - row1[-1]).seconds > 1:
    print (row1[-1] + pd.Timedelta('1s'))

我想要的是打印2017-06-13 16:38:16 2017-06-13 16:38:22 2017-06-13 16:38:32 值为Time_Stamp的整行，其中唯一的行是 2017-06-13 16:38:16 值超过 5.0 ，在这种情况下（基于示例代码），其c1

而不是：

415.7

我想像这样打印：

13/06/2017 16:38:16

打印完该行后，我必须使用415.7,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,13/06/2017 16:38:16 415.7,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,13/06/2017 16:38:22 415.7,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,13/06/2017 16:38:32 直接替换上方 c1 - 415.7的值。我该怎么做？

修改

要替换的内容：

pspike输出

中缺失行的0.0

1 个答案:

答案 0 :(得分：1)

我在这里有点困惑，因为你可以这样做：

pspike = timerange[timerange['c1'].gt(5.0)] #gr=greater than, lt=lower than

返回带有以下内容的数据框：

16  415.7   12.5    30.2    154.6   4675.2  1   -1  5199.4  0   50  0   2017-06-13 16:38:16

将列“c1”的值设置为0.0 

pspike["c1"] = 0.0

从第一行创建一个字符串（index = 0）：

','.join(pspike.astype(str).values.tolist()[0])

打印：

'0.0,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,2017-06-13 16:38:16'

<强>更新 

string = """c1,c2,v1,v2,p1,p2,r1,a1,f1,f2,f3,Time_Stamp
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:00
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:01
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:02
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:03
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:04
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:05
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:06
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:07
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:08
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:09
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:10
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:11
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:12
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:13
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:14
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:15
415.7,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,13/06/2017 16:38:16 
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:17
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:18
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:19
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:20
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:21
415.7,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,13/06/2017 16:38:22
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:23
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:24
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:25
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:26
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:27
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:28
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:29
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:30
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:31
415.7,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,13/06/2017 16:38:32
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:33
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:34
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:35
0,2.3,0.6,-0.9,-0.5,1,-1,941.0,0,50,0,13/06/2017 16:38:36"""

df = pd.read_csv(io.StringIO(string)) # reads data from string above
#Use : df = pd.read_csv('filename.csv')  for csv file (handling tons of data)
df["Time_Stamp"] = pd.to_datetime(df["Time_Stamp"]) # convert to Datetime
df_filter = df[df["c1"].le(0.5)] # new df with less or equal to 0.5
where = (df_filter[df_filter["Time_Stamp"].diff().dt.total_seconds() > 1] ["Time_Stamp"] - pd.Timedelta("1s")).astype(str).tolist() # Find where diff > 1 second
df_filter2 = df[df["Time_Stamp"].isin(where)] # Create new df with those
df_filter2["c1"] = 0.0 # Set c1 to 0.0

for index, row in df_filter2.iterrows():
    values = row.astype(str).tolist()
    print(','.join(values))

返回

0.0,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,2017-06-13 16:38:16
0.0,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,2017-06-13 16:38:22
0.0,12.5,30.2,154.6,4675.2,1,-1,5199.4,0,50,0,2017-06-13 16:38:32
相关问题
最新问题