CODEWITHSUNDEEP
pythonpandasdataframe
Robxaa798
Robxaa798

Reputation: 161

Two-point Euclidean distance from csv file

I want to calculate the distance between two points and label them. The problem is that the code doesn't work on more than 1 line. When there is 1 row, the program shows me result which I want:

enter image description here

This is an error when there is more than 1 line : "cannot convert the series to <class 'float'>"

This is my code:

data = pd.read_csv (r'C:\Users\DSAij\Documents\Projekt.csv') 
data.head()

choices_1 = ['short','medium','long']

if not ((data['x_start'] < data['x_end']) & (data['y_start'] < data['y_end'])).empty:
    conditions_1 = [
        ((math.sqrt((((data['x_end']) - (data['x_start']))**2) + ((data['y_end'])-(data['y_start']))**2)) < 5), 
        ((math.sqrt((((data['x_end']) - (data['x_start']))**2) + ((data['y_end'])-(data['y_start']))**2)) >= 5 and 
        (math.sqrt((((data['x_end']) - (data['x_start']))**2) + ((data['y_end'])-(data['y_start']))**2)) < 10),
        ((math.sqrt((((data['x_end']) - (data['x_start']))**2) + ((data['y_end'])-(data['y_start']))**2)) > 10)]
    
    data['Pass'] = np.select(conditions_1, choices_1)

  #  if not ((data['x_start'] < data['x_end']) & (data['y_start'] > data['y_end'])).empty:
   #     conditions_2 = [
    #        ((math.sqrt((((data['x_end']) - (data['x_start']))**2) + ((data['y_start'])-(data['y_end']))**2)) < 5), 
     #       ((math.sqrt((((data['x_end']) - (data['x_start']))**2) + ((data['y_start'])-(data['y_end']))**2)) >= 5 and 
      #      (math.sqrt((((data['x_end']) - (data['x_start']))**2) + ((data['y_start'])-(data['y_end']))**2)) < 10),
       #     ((math.sqrt((((data['x_end']) - (data['x_start']))**2) + ((data['y_start'])-(data['y_end']))**2)) > 10)]

#        data['Pass'] = np.select(conditions_2, choices_1)
        
 #   if not ((data['x_start'] > data['x_end']) & (data['y_start'] < data['y_end'])).empty:
  #      conditions_3 = [
   #         ((math.sqrt((((data['x_start']) - (data['x_end']))**2) + ((data['y_end'])-(data['y_start']))**2)) < 5), 
    #        ((math.sqrt((((data['x_start']) - (data['x_end']))**2) + ((data['y_end'])-(data['y_start']))**2)) >= 5 and 
     #       (math.sqrt((((data['x_start']) - (data['x_end']))**2) + ((data['y_end'])-(data['y_start']))**2)) < 10),
      #      ((math.sqrt((((data['x_start']) - (data['x_end']))**2) + ((data['y_end'])-(data['y_start']))**2)) > 10)]
        
      #  data['Pass'] = np.select(conditions_3, choices_1)
        
  #  if not ((data['x_start'] > data['x_end']) & (data['y_start'] > data['y_end'])).empty:
   #     conditions_4 = [
    #        ((math.sqrt((((data['x_start']) - (data['x_end']))**2) + ((data['y_start'])-(data['y_end']))**2)) < 5), 
     #       ((math.sqrt((((data['x_start']) - (data['x_end']))**2) + ((data['y_start'])-(data['y_end']))**2)) >= 5 and 
      #      (math.sqrt((((data['x_start']) - (data['x_end']))**2) + ((data['y_start'])-(data['y_end']))**2)) < 10),
       #     ((math.sqrt((((data['x_start']) - (data['x_end']))**2) + ((data['y_start'])-(data['y_end']))**2)) > 10)]

        #data['Pass'] = np.select(conditions_4, choices_1)

The part that is commented out is when the x_end is greater than x_start etc.

This is my data frame

enter image description here

Upvotes: 0

Views: 306

Answers (1)

dimitris_ps
dimitris_ps

Reputation: 5951

Try this

import pandas as pd
import numpy as np

#create a function that calculates what you want (i.e distance in this case)
def dist(x0, x1, y0, y1):
    return ((x1 - x0)**2 + (y1 - y0)**2)**(1/2)

# Your dataframe (please provide this yourself next time)
df = pd.DataFrame({'x_start':[24, 24, 24, 5], 
                   'x_end':[12, 36, 12, 12], 
                   'y_start':[35, 35, 95, 87], 
                   'y_end':[57, 57, 57, 57]})

#this calculates the distance
df['Pass'] = df.apply(lambda x: 
                      dist(x['x_start'], x['x_end'], x['y_start'], x['y_end']), axis=1) 

#this will apply your conditions
df['Pass'] = np.select(
                [df['Pass']<5, (df['Pass']<10) & (df['Pass']>=5), df['Pass']>=10], 
                ['short','medium','long'], 
                default=np.nan) 
df

Upvotes: 1

Related Questions