group by pandas examples
>>> n_by_state = df.groupby("state")["state"].count()
>>> n_by_state.head(10)
state
AK 16
AL 206
AR 117
AS 2
AZ 48
CA 361
CO 90
CT 240
DC 2
DE 97
Name: last_name, dtype: int64group by pandas examples
>>> n_by_state = df.groupby("state")["state"].count()
>>> n_by_state.head(10)
state
AK 16
AL 206
AR 117
AS 2
AZ 48
CA 361
CO 90
CT 240
DC 2
DE 97
Name: last_name, dtype: int64groupby and list
In [1]: df = pd.DataFrame( {'a':['A','A','B','B','B','C'], 'b':[1,2,5,5,4,6]})
df
Out[1]:
a b
0 A 1
1 A 2
2 B 5
3 B 5
4 B 4
5 C 6
In [2]: df.groupby('a')['b'].apply(list)
Out[2]:
a
A [1, 2]
B [5, 5, 4]
C [6]
Name: b, dtype: object
In [3]: df1 = df.groupby('a')['b'].apply(list).reset_index(name='new')
df1
Out[3]:
a new
0 A [1, 2]
1 B [5, 5, 4]
2 C [6]pandas groupby
data.groupby('month', as_index=False).agg({"duration": "sum"})pandas groupby
# usage example
gb = df.groupby(["col1", "col2"])
counts = gb.size().to_frame(name="counts")
count
(
counts.join(gb.agg({"col3": "mean"}).rename(columns={"col3": "col3_mean"}))
.join(gb.agg({"col4": "median"}).rename(columns={"col4": "col4_median"}))
.join(gb.agg({"col4": "min"}).rename(columns={"col4": "col4_min"}))
.reset_index()
)
# to create dataframe
keys = np.array(
[
["A", "B"],
["A", "B"],
["A", "B"],
["A", "B"],
["C", "D"],
["C", "D"],
["C", "D"],
["E", "F"],
["E", "F"],
["G", "H"],
]
)
df = pd.DataFrame(
np.hstack([keys, np.random.randn(10, 4).round(2)]), columns=["col1", "col2", "col3", "col4", "col5", "col6"]
)
df[["col3", "col4", "col5", "col6"]] = df[["col3", "col4", "col5", "col6"]].astype(float)Copyright © 2021 Codeinu
Forgot your account's password or having trouble logging into your Account? Don't worry, we'll help you to get back your account. Enter your email address and we'll send you a recovery link to reset your password. If you are experiencing problems resetting your password contact us
