#Create a Dataframe type of data structure from a CSV file>>>df=pd.read_csv ("Xxx.csv")#shape and length of the Dataframe type>>>Df.shape (38, 39)>>>Len (DF)38#headings and data types for each column>>>Df.columns>>>Df.dtypes#Index>>>Df.indexrangeindex (Start=0, stop=38, step=1)#Convert dataframe to numpy array>>>df.values#View Variable Types>>>type (DF)<class 'Pandas.core.frame.DataFrame'>#get a column of dataframe (the resulting data type is series)>>>type (DF)<class 'Pandas.core.frame.DataFrame'>>>> col=df['104']>>>type (col)<class 'pandas.core.series.Series'>#properties similar to Dataframe in series>>>Col.shape (38,)>>>Col.valuesarray ([301, 1051, 1657, 1852, 2057, 2258, 2938, 3418, 3718, 3938, 4148, 4568, 5068])>>>Col.indexrangeindex (Start=0, stop=38, step=1)>>>Col.name'104'#intercept the last few elements>>> col[-2:]36 6553637 65536Name:104, Dtype:int64>>> Type (col[-2:])<class 'pandas.core.series.Series'>#symbols of the Dataframe>>>np.sign (DF)>>> last_col=df.columns[-1]>>>np.sign (Df[last_col])#Head (take the first few lines) and tail (take a few lines)>>> Df.head (2)>>> Df.tail (2)#find a row of data by index>>> last_col=df.index[-1]>>>Last_col>>>Df.iloc[last_col]#find a column of data for a row by index>>> Df.iloc[2:9]#Iloc and IAT function the same>>> df.iloc[2,3]>>> df.iat[2,3]#Logical Lookup>>> df[df>Df.mean ()]#Statistical Calculations#Description Information>>>Df.describe ()#number of non-empty data>>>Df.count ()#average Absolute deviation (similar to standard deviation)>>>Df.mad ()#Number of median>>>Df.median ()#Minimum Value>>>df.min ()#Maximum Value>>>Df.max ()#The majority of>>>Df.mode ()#Standard deviation>>>df.std ()#Variance>>>Df.var ()#skewness coefficient (skewness, which indicates the degree of symmetry of the data)>>>Df.skew ()#Peak state function (Kurtosis, which indicates the degree of flattening of the data distribution graph)>>>Df.kurt ()#generate dataframe with a python dictionary>>> DF=PD. DataFrame ({'Weather':['Cold',' Hot'],' Food':['Soup','Ice Cream']})>>>DF Food Weather0 Soup Cold1Ice cream Hot#Group an attribute by type>>> Group=df.groupby ('Weather')>>> forName,groinchGroup: ...Print(name) ...Print(GRO) ... cold food weather0 soup Cold2Cake Coldhot Food weather1Ice cream Hot3Bread Hot>>>Group<pandas.core.groupby.groupby.dataframegroupby Object at 0x7f110c24d1d0>#first row, last line, average of each group>>> Group=df.groupby ('Weather')>>>Group.first () Food priceweather Cold Soup1Hot ice Cream2>>>group.last () food priceweather cold Cake3Hot Bread4>>>Group.mean () Priceweather Cold2 Hot3#View Grouping>>> G=df.groupby (['Weather',' Food'])>>>g.groups{(' Hot','Bread'): Int64index ([3], dtype='Int64'), ('Cold','Cake'): Int64index ([2], dtype='Int64'), (' Hot','Ice Cream'): Int64index ([1], dtype='Int64'), ('Cold','Soup'): Int64index ([0], dtype='Int64')}#Append attributes for grouping>>>G.agg ([Np.mean]) Price meanweather food Cold cake3Soup1Hot Bread4Ice Cream2#Intercept a few lines of data and connect>>> D=pd.concat ([df[:2],df[3:]])>>>D>>> D=pd.concat ([df[:2],df[3:]])>>>d food price Weather0 soup1Cold1 Ice Cream 2 Hot3 Bread 4 Hot>>> D.append (df[3:]) Food price Weather0 Soup1Cold1 Ice Cream 2 Hot3 Bread 4 Hot3 Bread 4 Hot
Python data processing tools using method collation