Seaborn 绘图代码

seaborn单变量、多变量及回归分析绘图
https://blog.csdn.net/llh_1178/article/details/78147822

Python数据科学分析速查表
https://github.com/iamseancheney/python-data-science-cheatsheet

subplots 的用法示例

使用 regplot() 和 lmplot() 都可以绘制回归关系，推荐 regplot()。

ig, ((ax1, ax2), (ax3, ax4),(ax5,ax6)) = plt.subplots(nrows=3, ncols=2, figsize=(14,10))

OverallQual_scatter_plot = pd.concat([train['SalePrice'],train['OverallQual']],axis = 1)
sns.regplot(x='OverallQual',y = 'SalePrice',data = OverallQual_scatter_plot,scatter= True, fit_reg=True, ax=ax1)

TotalBsmtSF_scatter_plot = pd.concat([train['SalePrice'],train['TotalBsmtSF']],axis = 1)
sns.regplot(x='TotalBsmtSF',y = 'SalePrice',data = TotalBsmtSF_scatter_plot,scatter= True, fit_reg=True, ax=ax2)

GrLivArea_scatter_plot = pd.concat([train['SalePrice'],train['GrLivArea']],axis = 1)
sns.regplot(x='GrLivArea',y = 'SalePrice',data = GrLivArea_scatter_plot,scatter= True, fit_reg=True, ax=ax3)

GarageArea_scatter_plot = pd.concat([train['SalePrice'],train['GarageArea']],axis = 1)
sns.regplot(x='GarageArea',y = 'SalePrice',data = GarageArea_scatter_plot,scatter= True, fit_reg=True, ax=ax4)

FullBath_scatter_plot = pd.concat([train['SalePrice'],train['FullBath']],axis = 1)
sns.regplot(x='FullBath',y = 'SalePrice',data = FullBath_scatter_plot,scatter= True, fit_reg=True, ax=ax5)

YearBuilt_scatter_plot = pd.concat([train['SalePrice'],train['YearBuilt']],axis = 1)
sns.regplot(x='YearBuilt',y = 'SalePrice',data = YearBuilt_scatter_plot,scatter= True, fit_reg=True, ax=ax6)

YearRemodAdd_scatter_plot = pd.concat([train['SalePrice'],train['YearRemodAdd']],axis = 1)
YearRemodAdd_scatter_plot.plot.scatter('YearRemodAdd','SalePrice')

频率分布直方图

plt.figure(figsize = (12,8))
sns.distplot(train.kurt(),color='r',axlabel ='Kurtosis',norm_hist= False, kde = True,rug = False)
plt.hist(train.kurt(),orientation = 'vertical',histtype = 'bar',label ='Kurtosis', color ='blue')
plt.show()

绘制热力图

f , ax = plt.subplots(figsize = (14,12))
plt.title('Correlation of Numeric Features with Sale Price',y=1,size=16)
sns.heatmap(correlation, square = True, vmax=0.8)

k= 11
cols = correlation.nlargest(k,'SalePrice')['SalePrice'].index
print(cols)
cm = np.corrcoef(train[cols].values.T)
f , ax = plt.subplots(figsize = (14,12))
sns.heatmap(cm, vmax=.8, linewidths=0.01, square=True,annot=True,cmap='viridis',
            linecolor="white",xticklabels = cols.values ,annot_kws = {'size':12}, yticklabels = cols.values)

很常用的一个 pairplot 图

sns.set()
columns = ['SalePrice','OverallQual','TotalBsmtSF','GrLivArea','GarageArea','FullBath','YearBuilt','YearRemodAdd']
sns.pairplot(train[columns],size = 2 ,kind ='scatter',diag_kind='kde')
plt.show()

使用 Pandas 绘制柱状图

saleprice_overall_quality= train.pivot_table(index ='OverallQual',values = 'SalePrice', aggfunc = np.median)
saleprice_overall_quality.plot(kind = 'bar',color = 'blue')
plt.xlabel('Overall Quality')
plt.ylabel('Median Sale Price')
plt.show()

pivot_table 得到数据透视表。

boxplot 绘制箱线图

var = 'OverallQual'
data = pd.concat([train['SalePrice'], train[var]], axis=1)
f, ax = plt.subplots(figsize=(12, 8))
fig = sns.boxplot(x=var, y="SalePrice", data=data)
fig.axis(ymin=0, ymax=800000);

var = 'Neighborhood'
data = pd.concat([train['SalePrice'], train[var]], axis=1)
f, ax = plt.subplots(figsize=(16, 10))
fig = sns.boxplot(x=var, y="SalePrice", data=data)
fig.axis(ymin=0, ymax=800000);
xt = plt.xticks(rotation=45)

连续绘制箱线图，下面这段代码有点厉害：

for c in categorical_features:
    train[c] = train[c].astype('category')
    if train[c].isnull().any():
        train[c] = train[c].cat.add_categories(['MISSING'])
        train[c] = train[c].fillna('MISSING')

def boxplot(x, y, **kwargs):
    sns.boxplot(x=x, y=y)
    x=plt.xticks(rotation=90)
f = pd.melt(train, id_vars=['SalePrice'], value_vars=categorical_features)
g = sns.FacetGrid(f, col="variable",  col_wrap=2, sharex=False, sharey=False, size=5)
g = g.map(boxplot, "value", "SalePrice")

计数图 countplot

plt.figure(figsize = (12, 6))
sns.countplot(x = 'Neighborhood', data = data)
xt = plt.xticks(rotation=45)

小提琴图

sns.violinplot('Functional', 'SalePrice', data = train)

pointplot

plt.figure(figsize=(8,10))
g1 = sns.pointplot(x='Neighborhood', y='SalePrice', 
                   data=train, hue='LotShape')
g1.set_xticklabels(g1.get_xticklabels(),rotation=90)
g1.set_title("Lotshape Based on Neighborhood", fontsize=15)
g1.set_xlabel("Neighborhood")
g1.set_ylabel("Sale Price", fontsize=12)
plt.show()