pandas.DataFrame documentation

第一個程序：

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

values = np.array([1, 3, 2, 4, 1, 6, 4])
example_df = pd.DataFrame({
    'value': values,
    'even': values % 2 == 0,
    'above_three': values > 3 
}, index=['a', 'b', 'c', 'd', 'e', 'f', 'g'])

# groupby() without as_index
first_even = example_df.groupby('even').first()
print(example_df)
print(first_even)
print(first_even['even']) # Causes an error. 'even' is no longer a column in the DataFrame

• 輸出結果：

# 第一個print
  above_three   even  value
a       False  False      1
b       False  False      3
c       False   True      2
d        True   True      4
e       False  False      1
f        True   True      6
g        True   True      4
# 第二個print
      above_three  value
even                    
False       False      1
True        False      2
# 第三個print
KeyError: 'even'

第二個程序：

first_even = example_df.groupby('even', as_index=False).first()
print(first_even)
print(first_even['even']) # Now 'even' is still a column in the DataFrame

• 輸出結果：

# 第一個print
   even above_three  value
0  False       False      1
1   True       False      2
# 第二個print
0    False
1     True
Name: even, dtype: bool

畫出地鐵流量分布圖：

nyc_subway_weather.csv
ctrl+s保存文件

import pandas as pd
filename = 'E:/Deep Learning/Udacity/Data_Analysis/nyc_subway_weather.csv'
subway_df = pd.read_csv(filename)
data_by_location = subway_df.groupby(['latitude','longitude'],as_index=False).mean()
data_by_location.head()['latitude']

scaled_entries = (data_by_location['ENTRIESn_hourly']/data_by_location['ENTRIESn_hourly'].std())

import matplotlib.pyplot as plt
plt.scatter(data_by_location['latitude'],data_by_location['longitude'],s=2*scaled_entries)
#scaled_entries乘以2使輸出點大小更適中
plt.show()

地鐵流量分布圖