create a function to create new rows in data frames based on the given parameters as list in pandas

Question

I have a data frame as shown below. where the data always will have one session. That means number of unique value in a column \'Session\' will be one always.

df:

Answer 1

Here is one way to do it

# function to create the u_cumulative
def create_u_columns (ser, threshold_ns = 0.8):
    # create a copy
    arr_ns = ser.to_numpy().copy()
    # array for latter insert
    arr_idx = np.zeros(len(ser), dtype=int)
    walkin_id = 0 #start at 0 not 1 for list indexing
    for i in range(len(arr_ns)-1):
        if arr_ns[i]>threshold_ns:
            # remove 1 - walkin
            arr_ns[i+1:] -= (1-walkin_no_show[walkin_id])
            # increment later idx to add
            arr_idx[i] = walkin_id+1
            walkin_id +=1
    # for the last row
    if arr_ns[-1]>threshold_ns:
        arr_idx[-1] = walkin_id+1
    #return a dataframe with both columns
    return pd.DataFrame({'u_cumulative': arr_ns, 'mask_idx':arr_idx}, index=ser.index)

Now define another function overbook_dfs

def overbook_dfs (df0, walkin_no_show, threshold_p ):
    l_res = [] #for result
    for th_p in threshold_p: #loop on threshold
        # create a copy of original dataframe
        df = df0.copy() 
        df[['u_cumulative','mask_idx']] = create_u_columns(df['Cumulative_no_show'],
                                                           threshold_ns=th_p)
        # select the rows
        df_toAdd = df.loc[df['mask_idx'].astype(bool), :].copy()
        # replace the values as wanted
        df_toAdd['No_Show'] = walkin_no_show[:len(df_toAdd)]
        df_toAdd['B_ID'] = 'walkin'+df_toAdd['mask_idx'].astype(str)
        df_toAdd['u_cumulative'] -= (1 - df_toAdd['No_Show'])
        # add 0.5 to index for later sort
        df_toAdd.index += 0.5 
        #append the result to a list
        l_res.append(pd.concat([df,df_toAdd])
                       .sort_index()
                       .reset_index(drop=True)
                       .drop('mask_idx', axis=1)
                    )
    return l_res

Finally, use it with the parameters

# parameters
walkin_no_show = [ 0.3, 0.2, 0.1, 0.4, 0.5, 0.4, 0.2, 0.7, 0.8]
threshold_p = [0.8, 0.9, 1.0, 1.1]

# call your function
df_0_8, df_0_9, df_1_0, df_1_1 = overbook_dfs(df, walkin_no_show, threshold_p)

print (df_0_9)
       B_ID  No_Show Session  slot_num  Cumulative_no_show  u_cumulative
0         1      0.4      s1         1                 0.4           0.4
1         2      0.3      s1         2                 0.7           0.7
2         3      0.8      s1         3                 1.5           1.5
3   walkin1      0.3      s1         3                 1.5           0.8
4         4      0.3      s1         4                 1.8           1.1
5   walkin2      0.2      s1         4                 1.8           0.3
6         5      0.6      s1         5                 2.4           0.9
7         6      0.8      s1         6                 3.2           1.7
8   walkin3      0.1      s1         6                 3.2           0.8
9         7      0.9      s1         7                 4.1           1.7
10  walkin4      0.4      s1         7                 4.1           1.1
11        8      0.4      s1         8                 4.5           1.5
12  walkin5      0.5      s1         8                 4.5           1.0
13        9      0.6      s1         9                 5.1           1.6
14  walkin6      0.4      s1         9                 5.1           1.0

Note this would fail if the list walkin_no_show is not long enough