numpy histogram

numpy.histogram()

import numpy as np 
   
a = np.array([89, 34, 56, 87, 90, 23, 45, 12, 65, 78, 9, 34, 12, 11, 2, 65, 78, 82, 28, 78]) 

histogram = np.histogram(a, bins= 2) 
print(histogram) 

(array([10, 10]), array([ 2., 46., 90.]))

 

import numpy as np

 

a = np.array([89, 34, 56, 87, 90, 23, 45, 12, 65, 78, 9, 34, 12, 11, 2, 65, 78, 82, 28, 78])

histogram = np.histogram(a, bins= 3)

print(histogram)

 

(array([7, 4, 9]), array([ 2. , 31.33333333, 60.66666667, 90. ]))

import numpy as np

 

a = np.array([89, 34, 56, 87, 90, 23, 45, 12, 65, 78, 9, 34, 12, 11, 2, 65, 78, 82, 28, 78])

histogram = np.histogram(a, bins= [0,30,60,90])

print(histogram)

(array([7, 4, 9]), array([ 0, 30, 60, 90]))

 

from matplotlib import pyplot as plt

import numpy as np

 

a = np.array([89, 34, 56, 87, 90, 23, 45, 12, 65, 78, 9, 34, 12, 11, 2, 65, 78, 82, 28, 78])

plt.hist(a, bins = [0,20,40,60,80,100])

plt.title("histogram")

plt.show()

import pandas as pd
import numpy as np

# read_csv() 함수로 df 생성
df = pd.read_csv('part5/auto-mpg.csv', header=None)

# 열 이름을 지정
df.columns = ['mpg', 'cylinders', 'displacement', 'horsepower', 'weight',
              'acceleration', 'model year', 'origin', 'name']
print(df['horsepower'])
# print('\n')
# print(df.dtypes)
# print(df['horsepower'].sample(3))
df['horsepower'].replace('?', np.nan, inplace=True)
df.dropna(subset=['horsepower'], axis=0, inplace=True)
df['horsepower'] = df['horsepower'].astype(float)

count, bin_dividers = np.histogram(df['horsepower'], bins=3)
# print(count)
print(bin_dividers)
bin_names = ['저출력', '보통출력', '고출력']
df['hp_bin'] = pd.cut(x=df['horsepower'], bins=bin_dividers,
                      labels=bin_names,
                      include_lowest=True)
print(df[['horsepower', 'hp_bin']].head(10))
horsepower_dummies = pd.get_dummies(df['hp_bin'])
print(horsepower_dummies.head(10))