Efficient way to assign values from another column pandas df

Question

I\'m trying to create a more efficient script that creates a new column based off values in another column. The script below performs this but I can only select

Answer 1

You can use:

def f(x):
    #get unique days
    u = x['Day'].unique()
    #mapping dictionary
    d = dict(zip(u, np.arange(len(u)) // 3 + 1))
    x['new'] = x['Day'].map(d)
    return x

df = df.groupby('Location', sort=False).apply(f)
#add Location column
s = df['new'].astype(str) + df['Location']
#encoding by factorize
df['new'] = pd.Series(pd.factorize(s)[0] + 1).map(str).radd('C')
print (df)
      Day Location new
0     Mon     Home  C1
1    Tues     Home  C1
2     Wed     Away  C2
3     Wed     Home  C1
4   Thurs     Away  C2
5   Thurs     Home  C3
6     Fri     Home  C3
7     Mon     Home  C1
8     Sat     Home  C3
9     Fri     Away  C2
10    Sun     Home  C4

Answer 2

Not as pretty, but much faster than the groupby/apply method...

def get_ordered_unique(a):
    u, idx = np.unique(a, return_index=True)
    # get ordered unique values
    return a[np.sort(idx)]

# split ordered unique value array into arrays of size 3
def find_ugrps(a):
    ord_u = get_ordered_unique(a)

    if ord_u.size > 3:
        split_idxs = [i for i in range(1, ord_u.size) if i % 3 == 0]
        u_grps = np.split(ord_u, split_idxs)
    else:
        u_grps = [ord_u]

    return u_grps

locs = pd.factorize(df.Location)[0] + 1
days = pd.factorize(df.Day)[0] + 1

assign = np.zeros(days.size).astype(int)
unique_locs = get_ordered_unique(locs)

i = 0
for loc in unique_locs:
    i += 1
    loc_idxs = np.where(locs == loc)[0]
    # find the ordered unique day values for each loc val slice
    these_unique_days = get_ordered_unique(days[loc_idxs])
    # split into ordered groups of three
    these_3day_grps = find_ugrps(these_unique_days)
    # assign integer for days found within each group
    for ugrp in these_3day_grps:
        day_idxs = np.where(np.isin(days[loc_idxs], ugrp))[0]
        np.put(assign, loc_idxs[day_idxs], i)
        i += 1

# set proper ordering within assign array using factorize
df['Assign'] = (pd.factorize(assign)[0] + 1)
df['Assign'] = 'C' + df['Assign'].astype(str)

print(df)

      Day Location Assign
0     Mon     Home     C1
1    Tues     Home     C1
2     Wed     Away     C2
3     Wed     Home     C1
4   Thurs     Away     C2
5   Thurs     Home     C3
6     Fri     Home     C3
7     Mon     Home     C1
8     Sat     Home     C3
9     Fri     Away     C2
10    Sun     Home     C4

Answer 3

# DataFrame Given
df = pd.DataFrame({
    'Day' : ['Mon','Tues','Mon','Wed','Thurs','Fri','Mon','Sat','Sun','Tues'],                 
    'Location' : ['Home','Home','Away','Home','Home','Home','Home','Home','Home','Away'],                   
     })
Unique_group = ['Mon','Tues','Wed']
df['Group'] = df['Day'].apply(lambda x:1 if x in Unique_group else 2)
df['Assign'] = np.zeros(len(df))
# Assigning the ditionary values for output from numeric
vals = dict([(i,'C'+str(i)) for i in range(len(df))])

Loop to cut the dataframe for each line and checking the previous 'Assign' column info to assign new value

for i in range(1,len(df)+1,1):
    # Slicing the Dataframe line by line
    df1 = df[:i]
    # Incorporating the conditions of Group and Location
    df1 = df1[(df1.Location == df1.Location.loc[i-1]) & (df1.Group == df1.Group.loc[i-1]) ]
    # Writing the 'Assign' value for the first line of sliced df
    if len(df1)==1:
        df.loc[i-1,'Assign'] = df[:i].Assign.max()+1
    # Writing the 'Assign value based on previous values if it has contiuos 2 values of same group
    elif (df1.Assign.value_counts()[df1.Assign.max()] <3):
        df.loc[i-1,'Assign'] = df1.Assign.max()
    # Writing 'Assign' value for new group
    else:
        df.loc[i-1,'Assign'] = df[:i]['Assign'].max()+1
df.Assign = df.Assign.map(vals)

Out:

     Day    Location    Group   Assign
0   Mon Home    1   C1
1   Tues    Home    1   C1
2   Mon Away    1   C2
3   Wed Home    1   C1
4   Thurs   Home    2   C3
5   Fri Home    2   C3
6   Mon Home    1   C4
7   Sat Home    2   C3
8   Sun Home    2   C5
9   Tues    Away    1   C2

Answer 4

On the second attempt this works.

It was quite hard to understand the question.

I was sure that this should be done with pandas groupby() and dataframe merging, if you check the history of this reply you can see how I changed the answer to replace more slow Python code with fast Pandas code.

The code below first counts the unique values per location and then uses a helper data frame to create the final value.

I recommend pasting this code into a Jupyter notebook and to examine the intermediary steps.

import pandas as pd
import numpy as np

d = ({
    'Day' : ['Mon','Tues','Wed','Wed','Thurs','Thurs','Fri','Mon','Sat','Fri','Sun'],                 
    'Location' : ['Home','Home','Away','Home','Away','Home','Home','Home','Home','Away','Home'],        
    })

df = pd.DataFrame(data=d)

# including the example result
df["example"] = pd.Series(["C" + str(e) for e in [1, 1, 2, 1, 2, 3, 3, 1, 3, 2, 4]])

# this groups days per location
s_grouped = df.groupby(["Location"])["Day"].unique()

# This is the 3 unique indicator per location
df["Pre-Assign"] = df.apply(
    lambda x: 1 + list(s_grouped[x["Location"]]).index(x["Day"]) // 3, axis=1
)

# Now we want these unique per combination
df_pre = df[["Location", "Pre-Assign"]].drop_duplicates().reset_index().drop("index", 1)
df_pre["Assign"] = 'C' + (df_pre.index + 1).astype(str)

# result
df.merge(df_pre, on=["Location", "Pre-Assign"], how="left")

Result

Other data frames / series: