Python concatenates rows in dataframe and adds values

Question

I have a dataframe:

 Type:  Volume:
 Q     10
 Q     20 
 T     10 
 Q     10
 T     20
 T     20
 Q     10

and I want to combine type T in one line and add volume only if two (or more) Ts are consecutive

i.e. to:

 Q    10
 Q    20 
 T    10 
 Q    10 
 T    20+20=40
 Q    10

Is there any way to achieve this? would work DataFrame.groupby?

Answer 1

I think this will help. This code can handle any number of consecutive Ts, and you can even change which character to combine. I added comments to the code to explain what it does.

https://pastebin.com/FakbnaCj

import pandas as pd

def combine(df):
    combined = [] # Init empty list
    length = len(df.iloc[:,0]) # Get the number of rows in DataFrame
    i = 0
    while i < length:
        num_elements = num_elements_equal(df, i, 0, 'T') # Get the number of consecutive 'T's
        if num_elements <= 1: # If there are 1 or less T's, append only that element to combined, with the same type
            combined.append([df.iloc[i,0],df.iloc[i,1]])
        else: # Otherwise, append the sum of all the elements to combined, with 'T' type
            combined.append(['T', sum_elements(df, i, i+num_elements, 1)])
        i += max(num_elements, 1) # Increment i by the number of elements combined, with a min increment of 1
    return pd.DataFrame(combined, columns=df.columns) # Return as DataFrame

def num_elements_equal(df, start, column, value): # Counts the number of consecutive elements
    i = start
    num = 0
    while i < len(df.iloc[:,column]):
        if df.iloc[i,column] == value:
            num += 1
            i += 1
        else:
            return num
    return num

def sum_elements(df, start, end, column): # Sums the elements from start to end
    return sum(df.iloc[start:end, column])

frame = pd.DataFrame({"Type":   ["Q", "Q", "T", "Q", "T", "T", "Q"],
               "Volume": [10,   20,  10,  10,  20,  20,  10]})
print(combine(frame))

Answer 2

If you just need partial amounts, here is a little trick:

import numpy as np
import pandas as pd

df = pd.DataFrame({"Type":   ["Q", "Q", "T", "Q", "T", "T", "Q"],
                   "Volume": [10,   20,  10,  10,  20,  20,  10]})
s = np.diff(np.r_[0, df.Type == "T"])
s[s < 0] = 0
res = df.groupby(("Type", np.cumsum(s) - 1)).sum().loc["T"]
print(res)

Output:

   Volume
0      10
1      40