Use pandas cut function in Dask - pandas

Question

How can I use pd.cut() in Dask?
Because of the large dataset, I am not able to put the whole dataset into memory before finishing the pd.cut().
Current code that is working in Pandas but needs to be changed to Dask:
import pandas as pd
d = {'name': [1, 5, 1, 10, 5, 1], 'amount': [1, 5, 3, 8, 4, 1]}
df = pd.DataFrame(data=d)
#Groupby name and add column sum (of amounts) and count (number of grouped rows)
df = (df.groupby('name')['amount'].agg(['sum', 'count']).reset_index().sort_values(by='name', ascending=True))
print(df.head(15))
#Groupby bins and chnage sum and count based on grouped rows
df = df.groupby(pd.cut(df['name'],
bins=[0,4,8,100],
labels=['namebin1', 'namebin2', 'namebin3']))['sum', 'count'].sum().reset_index()
print(df.head(15))
Output:
name sum count
0 namebin1 5 3
1 namebin2 9 2
2 namebin3 8 1
I tried:
import pandas as pd
import dask.dataframe as dd
d = {'name': [1, 5, 1, 10, 5, 1], 'amount': [1, 5, 3, 8, 4, 1]}
df = pd.DataFrame(data=d)
df = dd.from_pandas(df, npartitions=2)
df = df.groupby('name')['amount'].agg(['sum', 'count']).reset_index()
print(df.head(15))
df = df.groupby(df.map_partitions(pd.cut,
df['name'],
bins=[0,4,8,100],
labels=['namebin1', 'namebin2', 'namebin3']))['sum', 'count'].sum().reset_index()
print(df.head(15))
Gives error:
TypeError("cut() got multiple values for argument 'bins'",)

Answer 1

The reason why you're seeing this error is that pd.cut() is being called with the partition as the first argument which it doesn't expect (see the docs).
You can wrap it in a custom function and call that instead, like so:
import pandas as pd
import dask.dataframe as dd
def custom_cut(partition, bins, labels):
result = pd.cut(x=partition["name"], bins=bins, labels=labels)
return result
d = {'name': [1, 5, 1, 10, 5, 1], 'amount': [1, 5, 3, 8, 4, 1]}
df = pd.DataFrame(data=d)
df = dd.from_pandas(df, npartitions=2)
df = df.groupby('name')['amount'].agg(['sum', 'count']).reset_index()
df = df.groupby(df.map_partitions(custom_cut,
bins=[0,4,8,100],
labels=['namebin1', 'namebin2', 'namebin3']))[['sum', 'count']].sum().reset_index()
df.compute()
name sum count
namebin1 5 3
namebin2 9 2
namebin3 8 1