Pandas学习笔记

       Pandas是python的一个数据分析包，最初由AQR Capital Management于2008年4月开发，并于2009年底开源出来，目前由专注于Python数据包开发的PyData开发team继续开发和维护，属于PyData项目的一部分。Pandas最初被作为金融数据分析工具而开发出来，因此，pandas为时间序列分析提供了很好的支持。 Pandas的名称来自于面板数据（panel data）和python数据分析（data analysis）。panel data是经济学中关于多维数据集的一个术语，在Pandas中也提供了panel的数据类型。

In [1]: import pandasIn [2]: food_info = pandas.read_csv("food_info.csv")//读取本地csv文件        print type(food_info)//打印数据类型print "-------------------------"        print food_info.dtypes//数据中的类型集合        print help(pandas.read_csv)//打印帮助文档Out[2]: <class 'pandas.core.frame.DataFrame'>//pandas的主要数据类型        -------------------------        NDB_No               int64        Shrt_Desc           object//相当于string        Water_(g)          float64        Energ_Kcal           int64        Protein_(g)        float64In [3]: food_info.head()//读取数据的前5行        food_info.head(3)//读取前3行food_info.tail(4)//读取尾4行food_info.columns//获取所有的列名food_info.shape//查看数据的规模(m行n列)Out[3]: NDB_NoShrt_DescWater_(g)Energ_KcalProtein_(g)Lipid_Tot_(g)Ash_(g)Carbohydrt_(g)Fiber_TD_(g)Sugar_Tot_(g)...Vit_A_IUVit_A_RAEVit_E_(mg)Vit_D_mcgVit_D_IUVit_K_(mcg)FA_Sat_(g)FA_Mono_(g)FA_Poly_(g)Cholestrl_(mg)           01001BUTTER WITH SALT15.877170.8581.112.110.060.00.06...2499.0684.02.321.560.07.051.36821.0213.043215.0           11002BUTTER WHIPPED WITH SALT15.877170.8581.112.110.060.00.06...2499.0684.02.321.560.07.050.48923.4263.012219.0           21003BUTTER OIL ANHYDROUS0.248760.2899.480.000.000.00.00...3069.0840.02.801.873.08.661.92428.7323.694256.0           31004CHEESE BLUE42.4135321.4028.745.112.340.00.50...721.0198.00.250.521.02.418.6697.7780.80075.0           41005CHEESE BRICK41.1137123.2429.683.182.790.00.51...1080.0292.00.260.522.02.518.7648.5980.78494.0           5 rows × 36 columnsIn [4]: food_info.loc[0]//读取第1行数据        food_info.loc[3:6]//读取3，4,5,6行ndb_col = food_info["NDB_No"]//读取"NDB_No"列columns = ["NDB_No","Shrt_Desc"]N_S = food_info[columns]//读取"NDB_No"和"Shrt_Desc"列In [5]: columns = food_info.columns.tolist()//获取列名列表        print columns        gram_columns = []        for c in columns:           if c.endswith("(g)")://找出以(g)结尾的列              gram_columns.append(c)        gram_df = food_info[gram_columns]        print gram_dfOut[5]: ['NDB_No', 'Shrt_Desc', 'Water_(g)', 'Energ_Kcal', 'Protein_(g)', 'Lipid_Tot_(g)', 'Ash_(g)', 'Carbohydrt_(g)', 'Fiber_TD_(g)', 'Sugar_Tot_(g)', 'Calcium_(mg)', 'Iron_(mg)', 'Magnesium_(mg)', 'Phosphorus_(mg)', 'Potassium_(mg)', 'Sodium_(mg)', 'Zinc_(mg)', 'Copper_(mg)', 'Manganese_(mg)', 'Selenium_(mcg)', 'Vit_C_(mg)', 'Thiamin_(mg)', 'Riboflavin_(mg)', 'Niacin_(mg)', 'Vit_B6_(mg)', 'Vit_B12_(mcg)', 'Vit_A_IU', 'Vit_A_RAE', 'Vit_E_(mg)', 'Vit_D_mcg', 'Vit_D_IU', 'Vit_K_(mcg)', 'FA_Sat_(g)', 'FA_Mono_(g)', 'FA_Poly_(g)', 'Cholestrl_(mg)']        Water_(g)  Protein_(g)  Lipid_Tot_(g)  Ash_(g)  Carbohydrt_(g)  \        0      15.87         0.85          81.11     2.11            0.06           Fiber_TD_(g)  Sugar_Tot_(g)  FA_Sat_(g)  FA_Mono_(g)  FA_Poly_(g)          0           0.0           0.06      51.368       21.021        3.043 In [6]: food_info.sort_values("Water_(g)",inplace=True)//默认升序排序,inplace表示是否重新在原来数据上排序        print food_info["Water_(g)"]        food_info.sort_values("Water_(g)",inplace=True,ascending=False)//降序排序        print "-------------------------"print food_info["Water_(g)"]Out[6]:676       0.00        743       0.00        744       0.00        745       0.00        758       0.00        761       0.00-------------------------4209    100.00        4377    100.00        4378    100.00        4376    100.00        4348    100.00        4404     99.98        4372     99.98In [7]: import pandas as pd        import numpy as np        titanic_survival = pd.read_csv("titanic_train.csv")//泰坦尼克号船员获救信息        titanic_survival.head()Out[7]:PassengerIdSurvivedPclassNameSexAgeSibSpParchTicketFareCabinEmbarked               0103Braund, Mr. Owen Harrismale22.010A/5 211717.2500NaNS               1211Cumings, Mrs. John Bradley (Florence Briggs Th...female38.010PC 1759971.2833C85C               2313Heikkinen, Miss. Lainafemale26.000STON/O2. 31012827.9250NaNS               3411Futrelle, Mrs. Jacques Heath (Lily May Peel)female35.01011380353.1000C123S               4503Allen, Mr. William Henrymale35.0003734508.0500NaNSIn [8]: age = titanic_survival["Age"]        age.head(10)        age_is_null = pd.isnull(age)        print age_is_null//打印是否为null值print "-------------------------"        age_null_true = age[age_is_null]        print age_null_true//打印null值print "-------------------------"        age_null_count = len(age_null_true)        print age_null_count//统计null值个数Out[8]:0      False        1      False        2      False        3      False        4      False        5       True        6      False        -------------------------        5     NaN        17    NaN        19    NaN        26    NaN        28    NaN        29    NaN        31    NaN        -------------------------        177In [9]: good_ages = titanic_survival["Age"][age_is_null == False]//去除null后求平均年龄        mean_age = sum(good_ages)/len(good_ages)        print mean_ageOut[9]:29.6991176471In [10]: correct_mean_age = titanic_survival["Age"].mean()//直接求平均年龄         print correct_mean_ageOut[10]: 29.6991176471//pivot_table数据透视表函数，统计每个等级仓位的获救概率In [11]: passenger_survival = titanic_survival.pivot_table(index="Pclass",values="Survived",aggfunc=np.mean)         print passenger_survivalOut[11]:         Survived        Pclass                    1       0.629630          2       0.472826          3       0.242363//统计每个等级仓位人的平均年龄In [12]: passenger_mean_age = titanic_survival.pivot_table(index="Pclass",values="Age")         print passenger_mean_ageOut[12]:          Age        Pclass                    1       38.233441          2       29.877630          3       25.140620//求出变量"Embarked"和"Fare","Survived"之间的关系求和In [13]: port_stats = titanic_survival.pivot_table(index="Embarked",values=["Fare","Survived"],aggfunc=np.sum)         print port_statsOut[13]:                 Fare  Survived         Embarked                               C         10072.2962        93         Q          1022.2543        30         S         17439.3988       217In [14]: drop_na_columns = titanic_survival.dropna(axis=1)//去掉有空值的列         print drop_na_columns         new_titanic_survival = titanic_survival.dropna(axis=0,subset=["Age","Sex"])//去掉"Age","Sex"列有空值的行         print new_titanic_survivalOut[14]: 883  C.A./SOTON 34068   10.5000           884   SOTON/OQ 392076    7.0500           885            382652   29.1250           886            211536   13.0000           887            112053   30.0000           888        W./C. 6607   23.4500           889            111369   30.0000           890            370376    7.7500           [891 rows x 9 columns]          885      5            382652   29.1250          NaN        Q           886      0            211536   13.0000          NaN        S           887      0            112053   30.0000          B42        S           889      0            111369   30.0000         C148        C           890      0            370376    7.7500          NaN        Q           [714 rows x 12 columns]