python类countplot()的实例源码

def factor_plot(dataFrame, factors, prediction, color="Set3"):
    # First, plot the total for each factor. Then, plot the total for each
    # factor for the prediction variable (so in a conversion example, how
    # many people converted, revenue per country, etc.)

    # These refer to the rows and columns of the axis numpy array; not the
    # data itself.

    row = 0
    column = 0
    sns.set(style="whitegrid")
    # TODO: Set the width based on the max number of unique
    # values for the factors.

    plots = plt.subplots(len(factors), 2, figsize=(8,12))
    # It should
    for factor in factors:
        sns.countplot(x=factor, palette="Set3", data=dataFrame,
                      ax=plots[1][row][column])
        # Then print the total for each prediction
        sns.barplot(x=factor, y=prediction, data=dataFrame,
        ax=plots[1][row][column+1])
        row += 1
    plt.tight_layout() # Need this or else plots will crash into each other

def weather_distribution(self):
        data_dir = g_singletonDataFilePath.getTrainDir()
        self.gapdf = self.load_weatherdf(data_dir)
        print self.gapdf['weather'].describe()
#         sns.distplot(self.gapdf['gap'],kde=False, bins=100);

        sns.countplot(x="weather", data=self.gapdf, palette="Greens_d");
        plt.title('Countplot of Weather')
#         self.gapdf['weather'].plot(kind='bar')
#         plt.xlabel('Weather')
#         plt.title('Histogram of Weather')
        return

def PlotBarChart(CategoricalVar, data, XName):
    sns.countplot(CategoricalVar, data=data)
    plt.xlabel(XName)
    plt.title( XName + ' Bar Chart')
    plt.show()

def explore_feature_variation(self, col=None, use_target=False, **kwargs):
        '''
        Produces univariate plots of a given set of columns. Barplots are used
        for categorical columns while histograms (with fitted density functinos)
        are used for numerical columns.

        If use_target is true, then the variation of the given set of columns
        with respect to the response variable are used (e.g., 2d scatter 
        plots, boxplots, etc).

        Parameters
        ----------
        col : a string of a column name, or a list of many columns names or
                None (default). If col is None, all columns will be used.
        use_target : bool, default False
            Whether to use the target column in the plots.
        **kwargs: additional arguments to be passed to seaborn's distplot or
            to pandas's plotting utilities..
        '''            
        self._validate_params(params_list   = {'col':col},
                              expected_types= {'col':[str,list,type(None)]})        


        if type(col) is str: col = [col]
        if col is None: col = self._get_all_features()
        if use_target == False:
            for column in col:
                if self.is_numeric(self.df[column]) == True:
                    plt.figure(column)
                    #sns.despine(left=True)        
                    sns.distplot(self.df[column], color="m", **kwargs) 
                    plt.title(column)
                    plt.tight_layout()            
                    #plt.figure('boxplot')
                    #sns.boxplot(x=self.df[col], palette="PRGn")
                    #sns.despine(offset=10, trim=True)     
                elif self.is_categorical(self.df[column]) == True:            
                    #print self.df[column].describe()
                    plt.figure(column)
                    #sns.despine(left=True)    
                    if len(self.df[column].unique()) > 30:
                        self.df[column].value_counts()[:20][::-1].plot.barh(**kwargs)
                        #top = pd.DataFrame(data=top)
                        #sns.barplot(y=top.index, x=top)                        
                    else:
                        self.df[column].value_counts()[::-1].plot.barh(**kwargs)
                        #sns.countplot(y=self.df[column])                    
                    plt.title(column)
                    plt.tight_layout()
                else:
                    raise TypeError('TYPE IS NOT SUPPORTED')
        else: # use target variable
            for column in col:
                self.explore_features_covariation(col1=column, col2=self.y, **kwargs)

def countplots(wine_set):
    wine_set["quality"] = pd.Categorical(wine_set["quality"])
    seaborn.countplot(x="quality", data=wine_set)
    plt.xlabel("Quality level of wine (0-10 scale)")
    plt.show()

def variants_chrom(self):
        ''' Countplot of number of variants identified
            across all chromosomes.
        '''
        self.pdvcf.remove_scaffolds()
        plt.style.use('seaborn-deep')

        fig, ax = plt.subplots(figsize=(14, 7))
        sns.countplot(data=self.pdvcf.vcf, x='CHROM', palette='GnBu_d')

        ax.tick_params(labelsize=15)
        ax.set_ylabel('Variants', fontsize=20)
        ax.set_xlabel('Chromosome', fontsize=20)
        ax.set_title('Variants Identified Across Chromosomes', fontsize=25)
        return ax