Series结构

冷不防 2023-06-19 13:27 10阅读 0赞

1.  读取csv文件：
    
        import pandas as pd
        fandango = pd.read_csv('fandango_score_comparison.csv')
        series_film = fandango['FILM']
        print(series_film[0:5])
        series_rt = fandango['RottenTomatoes']
        print (series_rt[0:5])
    
    运行结果：  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70]
2.  制作Series
    
        # Import the Series object from pandas
        from pandas import Series
        
        film_names = series_film.values
        #print type(film_names)
        #print film_names
        rt_scores = series_rt.values
        #print rt_scores
        series_custom = Series(rt_scores , index=film_names)
        series_custom[['Minions (2015)', 'Leviathan (2014)']]
    
    运行结果：  
    ![在这里插入图片描述][2019120620205615.png]
3.  打印结果
    
        # int index is also aviable
        series_custom = Series(rt_scores , index=film_names)
        series_custom[['Minions (2015)', 'Leviathan (2014)']]
        fiveten = series_custom[5:10]
        print(fiveten)
    
    运行结果：  
    ![在这里插入图片描述][20191206202358185.png]
4.  排序
    
        original_index = series_custom.index.tolist()
        print (original_index)
        sorted_index = sorted(original_index)
        print(sorted_index)
        sorted_by_index = series_custom.reindex(sorted_index)
        print (sorted_by_index)
    
    运行结果：  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 1]
5.  排序索引
    
        sc2 = series_custom.sort_index()
        sc3 = series_custom.sort_values()
        #print(sc2[0:10])
        print(sc3[0:10])
    
    运行结果：  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 2]
6.  相加
    
        #The values in a Series object are treated as an ndarray, the core data type in NumPy
        import numpy as np
        # Add each value with each other
        print (np.add(series_custom, series_custom))
        # Apply sine function to each value
        np.sin(series_custom)
        # Return the highest value (will return a single value not a Series)
        np.max(series_custom)
    
    运行结果：  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 3]
7.  判断
    
        #will actually return a Series object with a boolean value for each film
        series_custom > 50
        series_greater_than_50 = series_custom[series_custom > 50]
        
        criteria_one = series_custom > 50
        criteria_two = series_custom < 75
        both_criteria = series_custom[criteria_one & criteria_two]
        print (both_criteria)
    
    运行结果：  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 4]
8.  运算
    
        #data alignment same index
        rt_critics = Series(fandango['RottenTomatoes'].values, index=fandango['FILM'])
        rt_users = Series(fandango['RottenTomatoes_User'].values, index=fandango['FILM'])
        rt_mean = (rt_critics + rt_users)/2
        
        print(rt_mean)
    
    运行结果：  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 5]
9.  set\_index
    
        #will return a new DataFrame that is indexed by the values in the specified column 
        #and will drop that column from the DataFrame
        #without the FILM column dropped 
        fandango = pd.read_csv('fandango_score_comparison.csv')
        print type(fandango)
        fandango_films = fandango.set_index('FILM', drop=False)
        #print(fandango_films.index)
    
    运行结果：  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 6]
10. 使用新索引
    
        # Slice using either bracket notation or loc[]
        fandango_films["Avengers: Age of Ultron (2015)":"Hot Tub Time Machine 2 (2015)"]
        fandango_films.loc["Avengers: Age of Ultron (2015)":"Hot Tub Time Machine 2 (2015)"]
        
        # Specific movie
        fandango_films.loc['Kumiko, The Treasure Hunter (2015)']
        
        # Selecting list of movies
        movies = ['Kumiko, The Treasure Hunter (2015)', 'Do You Believe? (2015)', 'Ant-Man (2015)']
        fandango_films.loc[movies]
        
        #When selecting multiple rows, a DataFrame is returned, 
        #but when selecting an individual row, a Series object is returned instead
    
    运行结果：  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 7]
11. 类型转化
    
        #The apply() method in Pandas allows us to specify Python logic
        #The apply() method requires you to pass in a vectorized operation 
        #that can be applied over each Series object.
        import numpy as np
        
        # returns the data types as a Series
        types = fandango_films.dtypes
        #print types
        # filter data types to just floats, index attributes returns just column names
        float_columns = types[types.values == 'float64'].index
        # use bracket notation to filter columns to just float columns
        float_df = fandango_films[float_columns]
        #print float_df
        # `x` is a Series object representing a column
        deviations = float_df.apply(lambda x: np.std(x))
        
        print(deviations)
    
    运行结果：  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 8]
12. 匿名函数std()函数用于计算标准差
    
        rt_mt_user = float_df[['RT_user_norm', 'Metacritic_user_nom']]
        rt_mt_user.apply(lambda x: np.std(x), axis=1)
    
    运行结果：  
    ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 9]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20191206201551510.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[2019120620205615.png]: https://img-blog.csdnimg.cn/2019120620205615.png
[20191206202358185.png]: https://img-blog.csdnimg.cn/20191206202358185.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20191206203422678.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 2]: https://img-blog.csdnimg.cn/2019120620355596.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 3]: https://img-blog.csdnimg.cn/20191206203821411.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 4]: https://img-blog.csdnimg.cn/20191206204027363.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 5]: https://img-blog.csdnimg.cn/20191206204233925.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 6]: https://img-blog.csdnimg.cn/20191206205026427.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 7]: https://img-blog.csdnimg.cn/20191206205853740.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 8]: https://img-blog.csdnimg.cn/20191206210112672.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg_size_16_color_FFFFFF_t_70 9]: https://img-blog.csdnimg.cn/20191206210438327.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MjI2MDEwMg==,size_16,color_FFFFFF,t_70