美文网首页
大师兄的Python机器学习笔记:数据预处理

大师兄的Python机器学习笔记:数据预处理

作者: superkmi | 来源:发表于2020-04-19 17:23 被阅读0次

    大师兄的Python机器学习笔记:Numpy库、Scipy库和Matplotlib库 (三)
    大师兄的Python机器学习笔记:数据重抽样

    一、获得数据

    • 机器学习需要大量的真实数据,可以通过互联网获得。
    1. 关于Kaggle
    • Kaggle(https://www.kaggle.com/)成立于2010年,是一个进行数据发掘和预测竞赛的在线平台。
    • 通过Kaggle,我们可以获得一些真实数据。
    2. 下载数据
    • 例如,我们可以在 此处下载美国各县的新冠肺炎数据。
    3. 读取数据
    • 由于数据基本都是.csv或者.json格式的,可以用python直接读取。
    import os
    from pprint import pprint
    
    def read_csv(file):
        # 读取数据并转换为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) # 为了让数据看起来更直观,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、判断数据缺失

    • 为了保证结果的准确性,需要对缺失数据进行处理。
    1. 筛选完整数据
    • 通过判断跳过不完整的数据。
    >>>import os
    >>>from csv import reader
    >>>from pprint import pprint
    
    >>>def read_csv(file):
    >>>    # 读取数据,跳过缺失的行或数据不完整的行 
    >>>    dataset = []
        
    >>>    with open(file,'r') as f:
    >>>        lines = list(reader(f))
    >>>        data_len = len(list(lines)[0]) # 获取标题列的长度
    
    >>>        for line in lines:
    >>>            if line and len(line) == data_len: # 如果行为空或者数据不完整则跳过
    >>>                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. 判断元素是否缺失**
    • 检查每个元素是否有缺失的
    >>>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. 判断缺失列
    • 检查每列是否包含缺失的元素。
    >>>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. 统计缺失元素
    • 统计每列缺失元素的数目。
    >>>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. 替换缺失值
    • 将缺失值替换为一个默认值。
    >>>import os
    >>>import pandas as pd
    >>>from pprint import pprint
    
    >>>def read_csv(file):
    >>>    # 获得文件中的数据
    >>>    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):
    >>>    # 替换空值
    >>>    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)) # 获得空列名
    >>>    new_data = replace_null(data,null_column_list,0) # 将空数据替换为0
    >>>    pprint(find_null_column(new_data))
    date      False
    county    False
    state     False
    fips      False
    cases     False
    deaths    False
    dtype: bool
    
    6. 缺失值比对
    • 判断两列的缺失值是否同时为空,并获得对比数据。
    >>>import os
    >>>import pandas as pd
    >>>from pprint import pprint
    
    >>>def read_csv(file):
    >>>    # 获得文件中的数据
    >>>    return pd.read_csv(file)
    
    >>>def compare_columns(col1,col2):
    >>>    # 对比两列的缺失值
    >>>    res = data[[col1,col2]][data[col2].isnull()==True]
    >>>    # 获得对比数据
    >>>    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. 数据类型转换

    • 为了保障结果的统一性,需要尽量将数据类型转换为浮点数(float)。
    >>>import os
    >>>import pandas as pd
    >>>from pprint import pprint
    
    >>>def read_csv(file):
    >>>    # 获得文件中的数据
    >>>    return pd.read_csv(file)
    
    >>>def to_float(data):
    >>>    for column in data:
    >>>        if column =='date':continue # 跳过日期
    >>>        if str(data[column][1]).isdigit(): # 如果是数字
    >>>            data[column] = data[column].astype('float') # 将列转为浮点数
    >>>    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. 数据特征缩放

    • 为了保证数据的特征具有相近的尺度,有时需要对数据进行特征缩放。
    1. 归一化(Rescaling)
    • 将所有特征缩放到0~1之间,使梯度下降法能更快的收敛。
    • 公式x' = \frac{x-min}{max-min}
    >>>import os
    >>>import pandas as pd
    >>>import numpy as np
    >>>from pprint import pprint
    
    >>>def read_csv(file):
    >>>    # 获得文件中的数据
    >>>    return pd.read_csv(file)
    
    >>>def to_float(data):
    >>>    # 将数据改为浮点数
    >>>    for column in data:
    >>>        if column =='date':continue # 跳过日期
    >>>        if str(data[column][1]).isdigit(): # 如果是数字
    >>>            data[column] = data[column].astype('float') # 将列转为浮点数
    >>>    return data
    
    >>>def min_max_normalization(data):
    >>>    # 归一化特征缩放
    >>>    for column in data:
    >>>        if column == 'date': continue  # 跳过日期
    >>>        if isinstance(data[column][1],float):  # 如果是浮点数
    >>>            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. 均值归一化(Mean Normalization)
    • 归一化的另一种方法,数据离平均值的距离。
    • 公式x' = \frac{x-average(x)}{max-min}
    >>>import os
    >>>import pandas as pd
    >>>import numpy as np
    >>>from pprint import pprint
    
    >>>def read_csv(file):
    >>>    # 获得文件中的数据
    >>>    return pd.read_csv(file)
    
    >>>def to_float(data):
    >>>    # 将数据改为浮点数
    >>>    for column in data:
    >>>        if column =='date':continue # 跳过日期
    >>>        if str(data[column][1]).isdigit(): # 如果是数字
    >>>            data[column] = data[column].astype('float') # 将列转为浮点数
    >>>    return data
    
    >>>def mean_normalization(data):
    >>>    # 均值归一化特征缩放
    >>>    for column in data:
    >>>        if column == 'date': continue  # 跳过日期
    >>>        if isinstance(data[column][1],float):  # 如果是浮点数
    >>>            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. 标准化(Standardlization)
    • 特征标准化使得数据中每个特征的值具有零均值和单位方差。
    • 公式x' = \frac{x-\bar{x}}{\sigma}
    >>>import os
    >>>import pandas as pd
    >>>import numpy as np
    >>>from pprint import pprint
    
    >>>def read_csv(file):
    >>>    # 获得文件中的数据
    >>>    return pd.read_csv(file)
    
    >>>def to_float(data):
    >>>    # 将数据改为浮点数
    >>>    for column in data:
    >>>        if column =='date':continue # 跳过日期
    >>>        if str(data[column][1]).isdigit(): # 如果是数字
    >>>            data[column] = data[column].astype('float') # 将列转为浮点数
    >>>    return data
    
    >>>def standardlization(data):
    >>>    # 标准化
    >>>    for column in data:
    >>>        if column == 'date': continue  # 跳过日期
    >>>        if isinstance(data[column][1],float):  # 如果是浮点数
    >>>            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. 缩放至单位长度(Scaling to Unit Length)
    • 该方法也在机器学习中常用。缩放特征向量的分量,将每个分量除以向量的欧几里得距离,使整个向量的长度为1。
    • 公式:x' = \frac{x}{||x||}
    >>>import os
    >>>import pandas as pd
    >>>import numpy as np
    >>>from pprint import pprint
    
    >>>def read_csv(file):
    >>>    # 获得文件中的数据
    >>>    return pd.read_csv(file)
    
    >>>def to_float(data):
    >>>    # 将数据改为浮点数
    >>>    for column in data:
    >>>        if column =='date':continue # 跳过日期
    >>>        if str(data[column][1]).isdigit(): # 如果是数字
    >>>            data[column] = data[column].astype('float') # 将列转为浮点数
    >>>    return data
    
    >>>def scaling_to_Unit_Length(data):
    >>>    #  缩放至单位长度
    >>>    for column in data:
    >>>        if column == 'date': continue  # 跳过日期
    >>>        if isinstance(data[column][1],float):  # 如果是浮点数
    >>>            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]
    

    参考资料


    相关文章

      网友评论

          本文标题:大师兄的Python机器学习笔记:数据预处理

          本文链接:https://www.haomeiwen.com/subject/oqjcvhtx.html