cut_and_dummy

In [1]:

import numpy as np
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
plt.style.use('ggplot')

%matplotlib inline

In [2]:

# http://pandas.pydata.org/pandas-docs/stable/generated/pandas.cut.html
# http://pandas.pydata.org/pandas-docs/stable/reshaping.html#computing-indicator-dummy-variables

In [3]:

np.random.seed(0)
df_for_cut = pd.DataFrame(np.random.randint(1, 99, 1000), columns=["age"])
df_for_cut.tail()

Out[3]:
age
995 36
996 89
997 50
998 80
999 85 
In [4]:

bins = list(range(0, 100+1, 10))
bins

Out[4]:

[0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100]

In [5]:

bins_labels = [str(b) + " - " + str(b + 10 - 1) for b in bins[:-1]]
bins_labels

Out[5]:

['0 - 9',
 '10 - 19',
 '20 - 29',
 '30 - 39',
 '40 - 49',
 '50 - 59',
 '60 - 69',
 '70 - 79',
 '80 - 89',
 '90 - 99']

In [6]:

df_for_cut["age_group"] = pd.cut(df_for_cut.age, bins=bins)
df_for_cut["age_group_right"] = pd.cut(df_for_cut.age, bins=bins, right=False)
df_for_cut["age_group_label_F"] = pd.cut(df_for_cut.age, bins=bins, labels=False)
df_for_cut["age_group_labels"] = pd.cut(df_for_cut.age, bins=bins, labels=bins_labels)
df_for_cut.tail()


Out[6]:
age age_group age_group_right age_group_label_F age_group_labels
995 36 (30, 40] [30, 40) 3 30 - 39
996 89 (80, 90] [80, 90) 8 80 - 89
997 50 (40, 50] [50, 60) 4 40 - 49
998 80 (70, 80] [80, 90) 7 70 - 79
999 85 (80, 90] [80, 90) 8 80 - 89 
In [7]:

df_for_cut.age_group.unique()

Out[7]:

[(40, 50], (60, 70], (0, 10], (80, 90], (20, 30], (30, 40], (70, 80], (10, 20], (50, 60], (90, 100]]
Categories (10, object): [(0, 10] < (10, 20] < (20, 30] < (30, 40] ... (60, 70] < (70, 80] < (80, 90] < (90, 100]]

In [8]:

df_for_cut.age_group_label_F.unique()

Out[8]:

array([4, 6, 0, 8, 2, 3, 7, 1, 5, 9])

In [9]:

dummies = pd.get_dummies(df_for_cut['age_group'], prefix='age_group')
df_for_cut_with_dummies = pd.concat([df_for_cut, dummies], axis=1)
df_for_cut_with_dummies.tail()

Out[9]:
age age_group age_group_right age_group_label_F age_group_labels age_group_(0, 10] age_group_(10, 20] age_group_(20, 30] age_group_(30, 40] age_group_(40, 50] age_group_(50, 60] age_group_(60, 70] age_group_(70, 80] age_group_(80, 90] age_group_(90, 100]
995 36 (30, 40] [30, 40) 3 30 - 39 0 0 0 1 0 0 0 0 0 0
996 89 (80, 90] [80, 90) 8 80 - 89 0 0 0 0 0 0 0 0 1 0
997 50 (40, 50] [50, 60) 4 40 - 49 0 0 0 0 1 0 0 0 0 0
998 80 (70, 80] [80, 90) 7 70 - 79 0 0 0 0 0 0 0 1 0 0
999 85 (80, 90] [80, 90) 8 80 - 89 0 0 0 0 0 0 0 0 1 0 
In [10]:

pd.get_dummies(pd.DataFrame({"a": list("AB"), "b": list("CD")}), prefix=list("ab"))

Out[10]:
a_A a_B b_C b_D
0 1 0 1 0
1 0 1 0 1 
In [11]:

factors = pd.Series(["B", np.nan, "a", np.nan, 123, 0.4, np.inf])
factors

Out[11]:

0      B
1    NaN
2      a
3    NaN
4    123
5    0.4
6    inf
dtype: object

In [12]:

factors.factorize()

Out[12]:

(array([ 0, -1,  1, -1,  2,  3,  4]),
 Index(['B', 'a', 123, 0.4, inf], dtype='object'))

In [19]:

qcuted_4 = pd.qcut(df_for_cut["age"], q=4)
qcuted_4.tail()

Out[19]:

995    (25, 49]
996    (74, 98]
997    (49, 74]
998    (74, 98]
999    (74, 98]
Name: age, dtype: category
Categories (4, object): [[1, 25] < (25, 49] < (49, 74] < (74, 98]]

In [20]:

qcuted_10 = pd.qcut(df_for_cut["age"], q=10)
qcuted_10.tail()

Out[20]:

995    (30, 39]
996    (80, 89]
997    (49, 59]
998    (70, 80]
999    (80, 89]
Name: age, dtype: category
Categories (10, object): [[1, 9] < (9, 20] < (20, 30] < (30, 39] ... (59, 70] < (70, 80] < (80, 89] < (89, 98]]

In [22]:

q = [0, .25, .5, .75, 1]
qcuted_list = pd.qcut(df_for_cut["age"], q=q)
qcuted_list.tail()

Out[22]:

995    (25, 49]
996    (74, 98]
997    (49, 74]
998    (74, 98]
999    (74, 98]
Name: age, dtype: category
Categories (4, object): [[1, 25] < (25, 49] < (49, 74] < (74, 98]]