大師兄的Python機器學習筆記:Numpy庫耿战、Scipy庫和Matplotlib庫 (三)
大師兄的Python機器學習筆記:數(shù)據(jù)重抽樣
一禽作、獲得數(shù)據(jù)
- 機器學習需要大量的真實數(shù)據(jù)碉熄,可以通過互聯(lián)網(wǎng)獲得直焙。
1. 關于Kaggle
- Kaggle(https://www.kaggle.com/)成立于2010年祠斧,是一個進行數(shù)據(jù)發(fā)掘和預測競賽的在線平臺盹兢。
- 通過Kaggle邻梆,我們可以獲得一些真實數(shù)據(jù)。
2. 下載數(shù)據(jù)
- 例如绎秒,我們可以在 此處下載美國各縣的新冠肺炎數(shù)據(jù)浦妄。
3. 讀取數(shù)據(jù)
- 由于數(shù)據(jù)基本都是.csv或者.json格式的,可以用python直接讀取。
import os
from pprint import pprint
def read_csv(file):
# 讀取數(shù)據(jù)并轉(zhuǎn)換為list
with open(file,'r') as f:
return list(f.readlines())
if __name__ == '__main__':
file_path = os.path.join('D:\\','dataset','us-counties.csv')
data = read_csv(file_path)
pprint(data) # 為了讓數(shù)據(jù)看起來更直觀剂娄,使用pprint
['date,county,state,fips,cases,deaths\n',
'2020-01-21,Snohomish,Washington,53061,1,0\n',
'2020-01-22,Snohomish,Washington,53061,1,0\n',
'2020-01-23,Snohomish,Washington,53061,1,0\n',
'2020-01-24,Cook,Illinois,17031,1,0\n',
'2020-01-24,Snohomish,Washington,53061,1,0\n',
'2020-01-25,Orange,California,06059,1,0\n',
'2020-01-25,Cook,Illinois,17031,1,0\n',
'2020-01-25,Snohomish,Washington,53061,1,0\n',
... ... (省略)
'2020-04-13,Teton,Wyoming,56039,56,0\n',
'2020-04-13,Uinta,Wyoming,56041,4,0\n',
'2020-04-13,Washakie,Wyoming,56043,4,0']
二蠢涝、判斷數(shù)據(jù)缺失
- 為了保證結(jié)果的準確性,需要對缺失數(shù)據(jù)進行處理阅懦。
1. 篩選完整數(shù)據(jù)
- 通過判斷跳過不完整的數(shù)據(jù)和二。
>>>import os
>>>from csv import reader
>>>from pprint import pprint
>>>def read_csv(file):
>>> # 讀取數(shù)據(jù),跳過缺失的行或數(shù)據(jù)不完整的行
>>> dataset = []
>>> with open(file,'r') as f:
>>> lines = list(reader(f))
>>> data_len = len(list(lines)[0]) # 獲取標題列的長度
>>> for line in lines:
>>> if line and len(line) == data_len: # 如果行為空或者數(shù)據(jù)不完整則跳過
>>> dataset.append(line)
>>> return dataset
>>>if __name__ == '__main__':
>>> file_path = os.path.join('D:\\','dataset','us-counties.csv')
>>> data = read_csv(file_path)
>>> pprint(data)
2. 判斷元素是否缺失**
- 檢查每個元素是否有缺失的
>>>import os
>>>import pandas as pd
>>>from pprint import pprint
>>>def read_csv(file):
>>> return pd.read_csv(file)
>>>def find_null(data):
>>> return data.isnull()
>>>if __name__ == '__main__':
>>> file_path = os.path.join('D:\\','dataset','us-counties.csv')
>>> data = read_csv(file_path)
>>> pprint(find_null(data))
date county state fips cases deaths
0 False False False False False False
1 False False False False False False
2 False False False False False False
3 False False False False False False
4 False False False False False False
... ... ... ... ... ... ...
56536 False False False False False False
56537 False False False False False False
56538 False False False False False False
56539 False False False False False False
56540 False False False False False False
[56541 rows x 6 columns]
3. 判斷缺失列
- 檢查每列是否包含缺失的元素耳胎。
>>>import os
>>>import pandas as pd
>>>from pprint import pprint
>>>def read_csv(file):
>>> return pd.read_csv(file)
>>>def find_null_column(data):
>>> return data.isnull().any()
>>>if __name__ == '__main__':
>>> file_path = os.path.join('D:\\','dataset','us-counties.csv')
>>> data = read_csv(file_path)
>>> pprint(find_null_column(data))
date False
county False
state False
fips True
cases False
deaths False
dtype: bool
4. 統(tǒng)計缺失元素
- 統(tǒng)計每列缺失元素的數(shù)目惯吕。
>>>import os
>>>import pandas as pd
>>>from pprint import pprint
>>>def read_csv(file):
>>> return pd.read_csv(file)
>>>def find_null_column(data):
>>> return data.isnull().any()
>>>def count_null(data,null_column):
>>> missing = data.columns[null_column].tolist()
>>> return data[missing].isnull().sum()
>>>if __name__ == '__main__':
>>> file_path = os.path.join('D:\\','dataset','us-counties.csv')
>>> data = read_csv(file_path)
>>> null_column = find_null_column(data)
>>> print(count_null(data,null_column))
fips 746
dtype: int64
5. 替換缺失值
- 將缺失值替換為一個默認值。
>>>import os
>>>import pandas as pd
>>>from pprint import pprint
>>>def read_csv(file):
>>> # 獲得文件中的數(shù)據(jù)
>>> return pd.read_csv(file)
>>>def find_null_column(data):
>>> # 返回所有包含空的列
>>> return data.isnull().any()
>>>def get_null_column_name(null_column):
>>> # 返回包含空列的列名
>>> return data.columns[null_column].tolist()
>>>def replace_null(data,columns,value):
>>> # 替換空值
>>> for column in columns:
>>> data.loc[data[column].isnull(),column] = value
>>> return data
>>>if __name__ == '__main__':
>>> file_path = os.path.join('D:\\','dataset','us-counties.csv')
>>> data = read_csv(file_path)
>>> null_column_list = get_null_column_name(find_null_column(data)) # 獲得空列名
>>> new_data = replace_null(data,null_column_list,0) # 將空數(shù)據(jù)替換為0
>>> pprint(find_null_column(new_data))
date False
county False
state False
fips False
cases False
deaths False
dtype: bool
6. 缺失值比對
- 判斷兩列的缺失值是否同時為空怕午,并獲得對比數(shù)據(jù)废登。
>>>import os
>>>import pandas as pd
>>>from pprint import pprint
>>>def read_csv(file):
>>> # 獲得文件中的數(shù)據(jù)
>>> return pd.read_csv(file)
>>>def compare_columns(col1,col2):
>>> # 對比兩列的缺失值
>>> res = data[[col1,col2]][data[col2].isnull()==True]
>>> # 獲得對比數(shù)據(jù)
>>> return res.describe()
>>>if __name__ == '__main__':
>>> file_path = os.path.join('D:\\','dataset','us-counties.csv')
>>> data = read_csv(file_path)
>>> pprint(compare_columns('state','fips'))
fips
count 0.0
mean NaN
std NaN
min NaN
25% NaN
50% NaN
75% NaN
max NaN
三. 數(shù)據(jù)類型轉(zhuǎn)換
- 為了保障結(jié)果的統(tǒng)一性,需要盡量將數(shù)據(jù)類型轉(zhuǎn)換為浮點數(shù)(float)郁惜。
>>>import os
>>>import pandas as pd
>>>from pprint import pprint
>>>def read_csv(file):
>>> # 獲得文件中的數(shù)據(jù)
>>> return pd.read_csv(file)
>>>def to_float(data):
>>> for column in data:
>>> if column =='date':continue # 跳過日期
>>> if str(data[column][1]).isdigit(): # 如果是數(shù)字
>>> data[column] = data[column].astype('float') # 將列轉(zhuǎn)為浮點數(shù)
>>> return data
>>>if __name__ == '__main__':
>>> file_path = os.path.join('D:\\','dataset','us-counties.csv')
>>> data = read_csv(file_path)
>>> print(to_float(data))
date county state fips cases deaths
0 2020-01-21 Snohomish Washington 53061.0 1.0 0.0
1 2020-01-22 Snohomish Washington 53061.0 1.0 0.0
2 2020-01-23 Snohomish Washington 53061.0 1.0 0.0
3 2020-01-24 Cook Illinois 17031.0 1.0 0.0
4 2020-01-24 Snohomish Washington 53061.0 1.0 0.0
... ... ... ... ... ... ...
56536 2020-04-13 Sublette Wyoming 56035.0 1.0 0.0
56537 2020-04-13 Sweetwater Wyoming 56037.0 9.0 0.0
56538 2020-04-13 Teton Wyoming 56039.0 56.0 0.0
56539 2020-04-13 Uinta Wyoming 56041.0 4.0 0.0
56540 2020-04-13 Washakie Wyoming 56043.0 4.0 0.0
[56541 rows x 6 columns]
四. 數(shù)據(jù)特征縮放
- 為了保證數(shù)據(jù)的特征具有相近的尺度堡距,有時需要對數(shù)據(jù)進行特征縮放。
1. 歸一化(Rescaling)
- 將所有特征縮放到0~1之間兆蕉,使梯度下降法能更快的收斂羽戒。
- 公式
>>>import os
>>>import pandas as pd
>>>import numpy as np
>>>from pprint import pprint
>>>def read_csv(file):
>>> # 獲得文件中的數(shù)據(jù)
>>> return pd.read_csv(file)
>>>def to_float(data):
>>> # 將數(shù)據(jù)改為浮點數(shù)
>>> for column in data:
>>> if column =='date':continue # 跳過日期
>>> if str(data[column][1]).isdigit(): # 如果是數(shù)字
>>> data[column] = data[column].astype('float') # 將列轉(zhuǎn)為浮點數(shù)
>>> return data
>>>def min_max_normalization(data):
>>> # 歸一化特征縮放
>>> for column in data:
>>> if column == 'date': continue # 跳過日期
>>> if isinstance(data[column][1],float): # 如果是浮點數(shù)
>>> x = data[column]
>>> x = (x - np.min(x))/(np.max(x)-np.min(x))
>>> data[column] = x
>>> return data
>>>if __name__ == '__main__':
>>> file_path = os.path.join('D:\\','dataset','us-counties.csv')
>>> data = read_csv(file_path)
>>> pprint(min_max_normalization(to_float(data)))
date county state fips cases deaths
0 2020-01-21 Snohomish Washington 0.945823 0.000008 0.0
1 2020-01-22 Snohomish Washington 0.945823 0.000008 0.0
2 2020-01-23 Snohomish Washington 0.945823 0.000008 0.0
3 2020-01-24 Cook Illinois 0.291232 0.000008 0.0
4 2020-01-24 Snohomish Washington 0.945823 0.000008 0.0
... ... ... ... ... ... ...
61966 2020-04-15 Sublette Wyoming 0.999855 0.000008 0.0
61967 2020-04-15 Sweetwater Wyoming 0.999891 0.000085 0.0
61968 2020-04-15 Teton Wyoming 0.999927 0.000499 0.0
61969 2020-04-15 Uinta Wyoming 0.999964 0.000034 0.0
61970 2020-04-15 Washakie Wyoming 1.000000 0.000034 0.0
[61971 rows x 6 columns]
2. 均值歸一化(Mean Normalization)
- 歸一化的另一種方法,數(shù)據(jù)離平均值的距離虎韵。
- 公式
>>>import os
>>>import pandas as pd
>>>import numpy as np
>>>from pprint import pprint
>>>def read_csv(file):
>>> # 獲得文件中的數(shù)據(jù)
>>> return pd.read_csv(file)
>>>def to_float(data):
>>> # 將數(shù)據(jù)改為浮點數(shù)
>>> for column in data:
>>> if column =='date':continue # 跳過日期
>>> if str(data[column][1]).isdigit(): # 如果是數(shù)字
>>> data[column] = data[column].astype('float') # 將列轉(zhuǎn)為浮點數(shù)
>>> return data
>>>def mean_normalization(data):
>>> # 均值歸一化特征縮放
>>> for column in data:
>>> if column == 'date': continue # 跳過日期
>>> if isinstance(data[column][1],float): # 如果是浮點數(shù)
>>> x = data[column]
>>> x = (x - np.mean(x))/(np.max(x)-np.min(x))
>>> data[column] = x
>>> return data
>>>if __name__ == '__main__':
>>> file_path = os.path.join('D:\\','dataset','us-counties.csv')
>>> data = read_csv(file_path)
>>> pprint(mean_normalization(to_float(data)))
date county state fips cases deaths
0 2020-01-21 Snohomish Washington 0.426211 -0.001020 -0.00049
1 2020-01-22 Snohomish Washington 0.426211 -0.001020 -0.00049
2 2020-01-23 Snohomish Washington 0.426211 -0.001020 -0.00049
3 2020-01-24 Cook Illinois -0.228380 -0.001020 -0.00049
4 2020-01-24 Snohomish Washington 0.426211 -0.001020 -0.00049
... ... ... ... ... ... ...
61966 2020-04-15 Sublette Wyoming 0.480243 -0.001020 -0.00049
61967 2020-04-15 Sweetwater Wyoming 0.480279 -0.000944 -0.00049
61968 2020-04-15 Teton Wyoming 0.480315 -0.000530 -0.00049
61969 2020-04-15 Uinta Wyoming 0.480352 -0.000995 -0.00049
61970 2020-04-15 Washakie Wyoming 0.480388 -0.000995 -0.00049
[61971 rows x 6 columns]
3. 標準化(Standardlization)
- 特征標準化使得數(shù)據(jù)中每個特征的值具有零均值和單位方差易稠。
- 公式
>>>import os
>>>import pandas as pd
>>>import numpy as np
>>>from pprint import pprint
>>>def read_csv(file):
>>> # 獲得文件中的數(shù)據(jù)
>>> return pd.read_csv(file)
>>>def to_float(data):
>>> # 將數(shù)據(jù)改為浮點數(shù)
>>> for column in data:
>>> if column =='date':continue # 跳過日期
>>> if str(data[column][1]).isdigit(): # 如果是數(shù)字
>>> data[column] = data[column].astype('float') # 將列轉(zhuǎn)為浮點數(shù)
>>> return data
>>>def standardlization(data):
>>> # 標準化
>>> for column in data:
>>> if column == 'date': continue # 跳過日期
>>> if isinstance(data[column][1],float): # 如果是浮點數(shù)
>>> x = data[column]
>>> x = (x - np.mean(x))/(np.var(x))
>>> data[column] = x
>>> return data
>>>if __name__ == '__main__':
>>> file_path = os.path.join('D:\\','dataset','us-counties.csv')
>>> data = read_csv(file_path)
>>> pprint(standardlization(to_float(data)))
date county state fips cases deaths
0 2020-01-21 Snohomish Washington 0.000097 -0.000052 -0.000585
1 2020-01-22 Snohomish Washington 0.000097 -0.000052 -0.000585
2 2020-01-23 Snohomish Washington 0.000097 -0.000052 -0.000585
3 2020-01-24 Cook Illinois -0.000052 -0.000052 -0.000585
4 2020-01-24 Snohomish Washington 0.000097 -0.000052 -0.000585
... ... ... ... ... ... ...
61966 2020-04-15 Sublette Wyoming 0.000110 -0.000052 -0.000585
61967 2020-04-15 Sweetwater Wyoming 0.000110 -0.000048 -0.000585
61968 2020-04-15 Teton Wyoming 0.000110 -0.000027 -0.000585
61969 2020-04-15 Uinta Wyoming 0.000110 -0.000051 -0.000585
61970 2020-04-15 Washakie Wyoming 0.000110 -0.000051 -0.000585
[61971 rows x 6 columns]
4. 縮放至單位長度(Scaling to Unit Length)
- 該方法也在機器學習中常用∪笆酰縮放特征向量的分量缩多,將每個分量除以向量的歐幾里得距離呆奕,使整個向量的長度為1养晋。
- 公式:
>>>import os
>>>import pandas as pd
>>>import numpy as np
>>>from pprint import pprint
>>>def read_csv(file):
>>> # 獲得文件中的數(shù)據(jù)
>>> return pd.read_csv(file)
>>>def to_float(data):
>>> # 將數(shù)據(jù)改為浮點數(shù)
>>> for column in data:
>>> if column =='date':continue # 跳過日期
>>> if str(data[column][1]).isdigit(): # 如果是數(shù)字
>>> data[column] = data[column].astype('float') # 將列轉(zhuǎn)為浮點數(shù)
>>> return data
>>>def scaling_to_Unit_Length(data):
>>> # 縮放至單位長度
>>> for column in data:
>>> if column == 'date': continue # 跳過日期
>>> if isinstance(data[column][1],float): # 如果是浮點數(shù)
>>> x = data[column]
>>> x = x/np.linalg.norm(x)
>>> data[column] = x
>>> return data
>>>if __name__ == '__main__':
>>> file_path = os.path.join('D:\\','dataset','us-counties.csv')
>>> data = read_csv(file_path)
>>> pprint(standardlization(to_float(data)))
date county state fips cases deaths
0 2020-01-21 Snohomish Washington 0.000097 -0.000052 -0.000585
1 2020-01-22 Snohomish Washington 0.000097 -0.000052 -0.000585
2 2020-01-23 Snohomish Washington 0.000097 -0.000052 -0.000585
3 2020-01-24 Cook Illinois -0.000052 -0.000052 -0.000585
4 2020-01-24 Snohomish Washington 0.000097 -0.000052 -0.000585
... ... ... ... ... ... ...
61966 2020-04-15 Sublette Wyoming 0.000110 -0.000052 -0.000585
61967 2020-04-15 Sweetwater Wyoming 0.000110 -0.000048 -0.000585
61968 2020-04-15 Teton Wyoming 0.000110 -0.000027 -0.000585
61969 2020-04-15 Uinta Wyoming 0.000110 -0.000051 -0.000585
61970 2020-04-15 Washakie Wyoming 0.000110 -0.000051 -0.000585
[61971 rows x 6 columns]
參考資料
- numpy包的應用 作者:你們都厲害
- 理解numpy的rollaxis與swapaxes函數(shù) 作者:liaoyuecai
- Python機器學習及分析工具:Scipy篇 作者:殉道者之花火
- 奇客谷 作者: 吳吃辣
- 統(tǒng)計stats模塊 作者: 火鍋俠