我试图将我的数据集字符串转换为浮点类型。这里有一些背景:
import pandas as pd
import numpy as np
import xlrd
file_location = "/Users/sekr2/Desktop/Jari/Leistungen/leistungen2_2017.xlsx"
workbook = xlrd.open_workbook(file_location)
sheet = workbook.sheet_by_index(0)
df = pd.read_excel("/Users/.../bla.xlsx")
df.head()
Leistungserbringer Anzahl Leistung AL TL TaxW Taxpunkte
0 McGregor Sarah 12 'Konsilium' 147.28 87.47 KVG 234.75
1 McGregor Sarah 12 'Grundberatung' 47.00 67.47 KVG 114.47
2 McGregor Sarah 12 'Extra 5min' 87.28 87.47 KVG 174.75
3 McGregor Sarah 12 'Respirator' 147.28 102.01 KVG 249.29
4 McGregor Sarah 12 'Besuch' 167.28 87.45 KVG 254.73
为了继续努力,我需要找到一种方法来创建一个新列:
df['Leistungswert'] = df['Taxpunkte'] * df['Anzahl'] * df['TaxW']
。
TaxW显示字符串' KVG'每个条目。我从数据中知道' KVG' = 0.89。我试图将字符串转换为浮点数而撞墙。我不能只使用float类型创建一个新列,因为此代码应该与其他输入一起使用。在TaxW列中,大约有7个不同的条目具有所有不同的值。
我很感谢有关此事的所有信息。
答案 0 :(得分:5)
假设TaxW
不是map_ = {'KVG' : 0.89, ... } # add more fields here
中唯一可能的字符串值,您应该将字符串映射存储到它们的浮点等效项中,如下所示:
Series.map
然后,您可以使用In [424]: df['Leistungswert'] = df['Taxpunkte'] * df['Anzahl'] * df['TaxW'].map(map_); df['Leistungswert']
Out[424]:
0 2507.1300
1 1222.5396
2 1866.3300
3 2662.4172
4 2720.5164
Name: Leistungswert, dtype: float64
:
df.transform
或者,您可以使用In [435]: df['Leistungswert'] = df.transform(lambda x: x['Taxpunkte'] * x['Anzahl'] * map_[x['TaxW']], axis=1); df['Lei
...: stungswert']
Out[435]:
0 2507.1300
1 1222.5396
2 1866.3300
3 2662.4172
4 2720.5164
Name: Leistungswert, dtype: float64
:
extension NSAttributedString {
convenience init(htmlString:String){
do {
try self.init(data: htmlString.data(using: .utf8)!, options: [NSDocumentTypeDocumentAttribute:NSHTMLTextDocumentType], documentAttributes: nil)
} catch {
print(error.localizedDescription)
}
}
func toHtml(location:Int,length:Int) -> String {
let documentAttributes = [NSDocumentTypeDocumentAttribute:NSHTMLTextDocumentType]
let range = NSRange.init(location: location, length: length)
do {
let htmlData = try self.data(from: range, documentAttributes: documentAttributes)
let htmlString = String(data: htmlData, encoding: .utf8)
return htmlString!
} catch {
return error.localizedDescription
}
}
}
答案 1 :(得分:5)
使用来自@COLDSPEED的map_
映射的替代解决方案:
In [237]: df.assign(TaxW=df['TaxW'].map(map_)) \
.eval("Leistungswert = Taxpunkte * Anzahl * TaxW", inplace=False)
Out[237]:
Leistungserbringer Anzahl Leistung AL TL TaxW Taxpunkte Leistungswert
0 McGregor Sarah 12 Konsilium 147.28 87.47 0.89 234.75 2507.1300
1 McGregor Sarah 12 Grundberatung 47.00 67.47 0.89 114.47 1222.5396
2 McGregor Sarah 12 Extra 5min 87.28 87.47 0.89 174.75 1866.3300
3 McGregor Sarah 12 Respirator 147.28 102.01 0.89 249.29 2662.4172
4 McGregor Sarah 12 Besuch 167.28 87.45 0.89 254.73 2720.5164