Consolidation from 2 DataFrames to 1

Question

I've written the code below. It works, but I'm sure I can do clearer and faster.

The idea is:

• I have 2 input DataFrames and I want 1 DataFrame as output.
• DF1 is like Name, Attribute1, Attribute2, Attribute3, ...
• DF2 is like Name1, Name2, Value1, Value2

I want, for each line of DF2 that NameX is replaced by the list of the Attribute(s) in DF1.

import pandas as pd

# dictionary 1
dico_1 = {
    'Name': ['A', 'B', 'C'],
    'Attr1': ['XXX', 'YYY', 'XXX'],
    'Attr2': ['YYY', 'ZZZ', 'YYY'],
}

dico_2 = {
    'Pair_1': ['A', 'B', 'B', 'A'],
    'Pair_2': ['B', 'C', 'A', 'C'],
    'V1': ['V1_AB', 'V1_BC', 'V1_BA', 'V1_AC'],
    'V2': ['V2_AB', 'V2_BC', 'V2_BA', 'V2_AC']
}

df1 = pd.DataFrame(dico_1)
df2 = pd.DataFrame(dico_2)


def cons(df1, df2, row):
    P1 = df2['Pair_1'][row]
    P2 = df2['Pair_2'][row]

    tmp1 = df1.loc[df1['Name'] == P1, "Attr1":"Attr2"]
    tmp2 = df1.loc[df1['Name'] == P2, "Attr1":"Attr2"]
    tmp3 = pd.DataFrame(df2.loc[row, "V1":"V2"]).transpose()
    tmp1.reset_index(drop=True, inplace=True)
    tmp2.reset_index(drop=True, inplace=True)
    tmp3.reset_index(drop=True, inplace=True)

    tmp1 = tmp1.add_suffix('_Pair1')
    tmp2 = tmp2.add_suffix('_Pair2')
    a = pd.concat([tmp1, tmp2, tmp3], axis=1)
    return a


df3 = pd.DataFrame(index=range(df2.shape[0]),
                   columns=['Attr1_Pair1', 'Attr2_Pair1', 'Attr1_Pair2', 'Attr2_Pair2', 'V1', 'V2'])
for row in range(df2.shape[0]):
    line = cons(df1, df2, row)
    df3.loc[row] = line.iloc[0]
df3

Answer 1

Let's try two merges instead:

import pandas as pd

dico_1 = {'Name': ['A', 'B', 'C'], 'Attr1': ['XXX', 'YYY', 'XXX'],
          'Attr2': ['YYY', 'ZZZ', 'YYY'], }

dico_2 = {'Pair_1': ['A', 'B', 'B', 'A'], 'Pair_2': ['B', 'C', 'A', 'C'],
          'V1': ['V1_AB', 'V1_BC', 'V1_BA', 'V1_AC'],
          'V2': ['V2_AB', 'V2_BC', 'V2_BA', 'V2_AC']}

df1 = pd.DataFrame(dico_1)
df2 = pd.DataFrame(dico_2)

# Merge with DF1 on Pair_1 then Merge again with DF1 on Pair_2
df3 = df2.merge(df1, left_on='Pair_1', right_on='Name') \
    .merge(df1, left_on='Pair_2', right_on='Name',
           suffixes=('_Pair1', '_Pair2'))

# Drop Extra Columns
df3 = df3.drop(columns=['Name_Pair1', 'Name_Pair2', 'Pair_1', 'Pair_2'])

print(df3)

df3:

      V1     V2 Attr1_Pair1 Attr2_Pair1 Attr1_Pair2 Attr2_Pair2
0  V1_AB  V2_AB         XXX         YYY         YYY         ZZZ
1  V1_BC  V2_BC         YYY         ZZZ         XXX         YYY
2  V1_BA  V2_BA         YYY         ZZZ         XXX         YYY
3  V1_AC  V2_AC         XXX         YYY         XXX         YYY