在Medium上看到一个比较系统的数据可视化方法，这里对此进行一下总结，也方便自己查阅。这里用到的数据集来着UCI Machine Learning Repository的Wine Quality Data Set ，具体特征如下截图：
image
下面对Wine数据集进行数据可视化分析。
首先导入必要的工具包：
import pandas as pd
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import matplotlib as mpl
import numpy as np
import seaborn as sns
%matplotlib inline
对数据进行预处理，设置新属性“wine_type”和“quality_label”：
white_wine = pd.read_csv('winequality-white.csv', sep=';')
red_wine = pd.read_csv('winequality-red.csv', sep=';')
# 新属性wine_type，对应酒的品种
red_wine['wine_type'] = 'red'
white_wine['wine_type'] = 'white'
# 将定量属性“quality”转换为定性变量
red_wine['quality_label'] = red_wine['quality'].apply(lambda value: 'low'
if value <= 5 else 'medium'
if value <= 7 else 'high')
red_wine['quality_label'] = pd.Categorical(red_wine['quality_label'],
categories=['low', 'medium', 'high'])
white_wine['quality_label'] = white_wine['quality'].apply(lambda value: 'low'
if value <= 5 else 'medium'
if value <= 7 else 'high')
white_wine['quality_label'] = pd.Categorical(white_wine['quality_label'],
categories=['low', 'medium', 'high'])
wines = pd.concat([red_wine, white_wine])
# 打乱数据集
wines = wines.sample(frac=1, random_state=42).reset_index(drop=True)
新的数据集wines
wines.head()
image.png
一.1维特征可视化分析
1 数值型变量可视化
直方图
wines.hist(bins=15, color='steelblue', edgecolor='black', linewidth=1.0,
xlabelsize=8, ylabelsize=8, grid=False)
plt.tight_layout(rect=(0, 0, 1.2, 1.2))
image.png
直方图与密度分析
# 绘制直方图
fig = plt.figure(figsize = (6,4))
title = fig.suptitle("Sulphates Content in Wine", fontsize=14)
fig.subplots_adjust(top=0.85, wspace=0.3)
ax = fig.add_subplot(1,1, 1)
ax.set_xlabel("Sulphates")
ax.set_ylabel("Frequency")
ax.text(1.2, 800, r'$\mu$='+str(round(wines['sulphates'].mean(),2)),
fontsize=12)
freq, bins, patches = ax.hist(wines['sulphates'], color='steelblue', bins=15,
edgecolor='black', linewidth=1)
# 绘制密度图
fig = plt.figure(figsize = (6, 4))
title = fig.suptitle("Sulphates Content in Wine", fontsize=14)
fig.subplots_adjust(top=0.85, wspace=0.3)
ax1 = fig.add_subplot(1,1, 1)
ax1.set_xlabel("Sulphates")
ax1.set_ylabel("Frequency")
sns.kdeplot(wines['sulphates'], ax=ax1, shade=True, color='steelblue')
image.png
2 类别性变量
fig = plt.figure(figsize = (6, 4))
title = fig.suptitle("Wine Quality Frequency", fontsize=14)
fig.subplots_adjust(top=0.85, wspace=0.3)
ax = fig.add_subplot(1,1, 1)
ax.set_xlabel("Quality")
ax.set_ylabel("Frequency")
w_q = wines['quality'].value_counts()
w_q = (list(w_q.index), list(w_q.values))
ax.tick_params(axis='both', which='major', labelsize=8.5)
bar = ax.bar(w_q[0], w_q[1], color='steelblue',
edgecolor='black', linewidth=1)
image.png
二.2维数据可视化分析
热力图（heatmap）
f, ax = plt.subplots(figsize=(10, 6))
corr = wines.corr()
hm = sns.heatmap(round(corr,2), annot=True, ax=ax, cmap="coolwarm",fmt='.2f',
linewidths=.05)
f.subplots_adjust(top=0.93)
t= f.suptitle('Wine Attributes Correlation Heatmap', fontsize=14)
image.png
散点图（scatter plots）
cols = ['density', 'residual sugar', 'total sulfur dioxide', 'fixed acidity']
pp = sns.pairplot(wines[cols], size=1.8, aspect=1.8,
plot_kws=dict(edgecolor="k", linewidth=0.5),
diag_kind="kde", diag_kws=dict(shade=True))
fig = pp.fig
fig.subplots_adjust(top=0.93, wspace=0.3)
t = fig.suptitle('Wine Attributes Pairwise Plots', fontsize=14)
image.png
折线图（parallel coordinate）
cols = ['density', 'residual sugar', 'total sulfur dioxide', 'fixed acidity']
subset_df = wines[cols]
from sklearn.preprocessing import StandardScaler
ss = StandardScaler()
scaled_df = ss.fit_transform(subset_df)
scaled_df = pd.DataFrame(scaled_df, columns=cols)
final_df = pd.concat([scaled_df, wines['wine_type']], axis=1)
final_df.head()
# plot parallel coordinates
from pandas.plotting import parallel_coordinates
pc = parallel_coordinates(final_df, 'wine_type', color=('#FFE888', '#FF9999'))
image.png
数值型变量关系分析
plt.scatter(wines['sulphates'], wines['alcohol'],
alpha=0.4, edgecolors='w')
plt.xlabel('Sulphates')
plt.ylabel('Alcohol')
plt.title('Wine Sulphates - Alcohol Content',y=1.05)
jp = sns.jointplot(x='sulphates', y='alcohol', data=wines,
kind='reg', space=0, size=5, ratio=4)
image.png
多重直方图（Multi-bar）
cp = sns.countplot(x="quality", hue="wine_type", data=wines,
palette={"red": "#FF9999", "white": "#FFE888"})
image.png
混合类型变量分析
fig = plt.figure(figsize = (6, 4))
title = fig.suptitle("Sulphates Content in Wine", fontsize=14)
fig.subplots_adjust(top=0.85, wspace=0.3)
ax = fig.add_subplot(1,1, 1)
ax.set_xlabel("Sulphates")
ax.set_ylabel("Frequency")
g = sns.FacetGrid(wines, hue='wine_type', palette={"red": "r", "white": "y"})
g.map(sns.distplot, 'sulphates', kde=False, bins=15, ax=ax)
ax.legend(title='Wine Type')
plt.close(2)
image.png
箱型图（Box Plots）
f, (ax) = plt.subplots(1, 1, figsize=(12, 4))
f.suptitle('Wine Quality - Alcohol Content', fontsize=14)
sns.boxplot(x="quality", y="alcohol", data=wines, ax=ax)
ax.set_xlabel("Wine Quality",size = 12,alpha=0.8)
ax.set_ylabel("Wine Alcohol %",size = 12,alpha=0.8)
image.png
提琴图（Violin Plots）
f, (ax) = plt.subplots(1, 1, figsize=(12, 4))
f.suptitle('Wine Quality - Sulphates Content', fontsize=14)
sns.violinplot(x="quality", y="sulphates", data=wines, ax=ax)
ax.set_xlabel("Wine Quality",size = 12,alpha=0.8)
ax.set_ylabel("Wine Sulphates",size = 12,alpha=0.8)
image.png
三.3维数据可视化分析
利用scatter plot中的hue选项
cols = ['density', 'residual sugar', 'total sulfur dioxide', 'fixed acidity', 'wine_type']
pp = sns.pairplot(wines[cols], hue='wine_type', size=1.8, aspect=1.8,
palette={"red": "#FF9999", "white": "#FFE888"},
plot_kws=dict(edgecolor="black", linewidth=0.5))
fig = pp.fig
fig.subplots_adjust(top=0.93, wspace=0.3)
t = fig.suptitle('Wine Attributes Pairwise Plots', fontsize=14)
image.png
三种连续性数值变量length, breadth和depth的可视化（Scatter）
fig = plt.figure(figsize=(8, 6))
ax = fig.add_subplot(111, projection='3d')
xs = wines['residual sugar']
ys = wines['fixed acidity']
zs = wines['alcohol']
ax.scatter(xs, ys, zs, s=50, alpha=0.6, edgecolors='w')
ax.set_xlabel('Residual Sugar')
ax.set_ylabel('Fixed Acidity')
ax.set_zlabel('Alcohol')
image.png
三种连续性数值变量length, breadth和size的可视化（Bubble）
plt.scatter(wines['fixed acidity'], wines['alcohol'], s=wines['residual sugar']*25,
alpha=0.4, edgecolors='w')
plt.xlabel('Fixed Acidity')
plt.ylabel('Alcohol')
plt.title('Wine Alcohol Content - Fixed Acidity - Residual Sugar',y=1.05)
image.png
三种离散型变量wine_type，quality_label和quality的可视化（factorplot）
fc = sns.factorplot(x="quality", hue="wine_type", col="quality_label",
data=wines, kind="count",
palette={"red": "#FF9999", "white": "#FFE888"})
image.png
混合型变量sulphates，alcohol和wine_type的可视化（pairplot&kdeplot）
jp = sns.pairplot(wines, x_vars=["sulphates"], y_vars=["alcohol"], size=4.5,
hue="wine_type", palette={"red": "#FF9999", "white": "#FFE888"},
plot_kws=dict(edgecolor="k", linewidth=0.5))
lp = sns.lmplot(x='sulphates', y='alcohol', hue='wine_type',
palette={"red": "#FF9999", "white": "#FFE888"},
data=wines, fit_reg=True, legend=True,
scatter_kws=dict(edgecolor="k", linewidth=0.5))
image.png
ax = sns.kdeplot(white_wine['sulphates'], white_wine['alcohol'],
cmap="YlOrBr", shade=True, shade_lowest=False)
ax = sns.kdeplot(red_wine['sulphates'], red_wine['alcohol'],
cmap="Reds", shade=True, shade_lowest=False)
image.png
四.4维数据可视化分析
散点图1
fig = plt.figure(figsize=(8, 6))
t = fig.suptitle('Wine Residual Sugar - Alcohol Content - Acidity - Type', fontsize=14)
ax = fig.add_subplot(111, projection='3d')
xs = list(wines['residual sugar'])
ys = list(wines['alcohol'])
zs = list(wines['fixed acidity'])
data_points = [(x, y, z) for x, y, z in zip(xs, ys, zs)]
colors = ['red' if wt == 'red' else 'yellow' for wt in list(wines['wine_type'])]
for data, color in zip(data_points, colors):
x, y, z = data
ax.scatter(x, y, z, alpha=0.4, c=color, edgecolors='none', s=30)
ax.set_xlabel('Residual Sugar')
ax.set_ylabel('Alcohol')
ax.set_zlabel('Fixed Acidity')
image.png
散点图2
g = sns.FacetGrid(wines, col="wine_type", hue='quality_label',
col_order=['red', 'white'], hue_order=['low', 'medium', 'high'],
aspect=1.2, size=3.5, palette=sns.light_palette('navy', 4)[1:])
g.map(plt.scatter, "volatile acidity", "alcohol", alpha=0.9,
edgecolor='white', linewidth=0.5, s=100)
fig = g.fig
fig.subplots_adjust(top=0.8, wspace=0.3)
fig.suptitle('Wine Type - Alcohol - Quality - Acidity', fontsize=14)
l = g.add_legend(title='Wine Quality Class')
image.png
气泡图
size = wines['residual sugar']*25
fill_colors = ['#FF9999' if wt=='red' else '#FFE888' for wt in list(wines['wine_type'])]
edge_colors = ['red' if wt=='red' else 'orange' for wt in list(wines['wine_type'])]
plt.scatter(wines['fixed acidity'], wines['alcohol'], s=size,
alpha=0.4, color=fill_colors, edgecolors=edge_colors)
plt.xlabel('Fixed Acidity')
plt.ylabel('Alcohol')
plt.title('Wine Alcohol Content - Fixed Acidity - Residual Sugar - Type',y=1.05)
image.png
五.5维数据可视化分析
散点图
fig = plt.figure(figsize=(8, 6))
ax = fig.add_subplot(111, projection='3d')
t = fig.suptitle('Wine Residual Sugar - Alcohol Content - Acidity - Total Sulfur Dioxide - Type', fontsize=14)
xs = list(wines['residual sugar'])
ys = list(wines['alcohol'])
zs = list(wines['fixed acidity'])
data_points = [(x, y, z) for x, y, z in zip(xs, ys, zs)]
ss = list(wines['total sulfur dioxide'])
colors = ['red' if wt == 'red' else 'yellow' for wt in list(wines['wine_type'])]
for data, color, size in zip(data_points, colors, ss):
x, y, z = data
ax.scatter(x, y, z, alpha=0.4, c=color, edgecolors='none', s=size)
ax.set_xlabel('Residual Sugar')
ax.set_ylabel('Alcohol')
ax.set_zlabel('Fixed Acidity')
image.png
气泡图
g = sns.FacetGrid(wines, col="wine_type", hue='quality_label',
col_order=['red', 'white'], hue_order=['low', 'medium', 'high'],
aspect=1.2, size=3.5, palette=sns.light_palette('black', 4)[1:])
g.map(plt.scatter, "residual sugar", "alcohol", alpha=0.8,
edgecolor='white', linewidth=0.5, s=wines['total sulfur dioxide']*2)
fig = g.fig
fig.subplots_adjust(top=0.8, wspace=0.3)
fig.suptitle('Wine Type - Sulfur Dioxide - Residual Sugar - Alcohol - Quality', fontsize=14)
l = g.add_legend(title='Wine Quality Class')
image.png
六.6维数据可视化分析
散点图1
fig = plt.figure(figsize=(8, 6))
t = fig.suptitle('Wine Residual Sugar - Alcohol Content - Acidity - Total Sulfur Dioxide - Type - Quality', fontsize=14)
ax = fig.add_subplot(111, projection='3d')
xs = list(wines['residual sugar'])
ys = list(wines['alcohol'])
zs = list(wines['fixed acidity'])
data_points = [(x, y, z) for x, y, z in zip(xs, ys, zs)]
ss = list(wines['total sulfur dioxide'])
colors = ['red' if wt == 'red' else 'yellow' for wt in list(wines['wine_type'])]
markers = [',' if q == 'high' else 'x' if q == 'medium' else 'o' for q in list(wines['quality_label'])]
for data, color, size, mark in zip(data_points, colors, ss, markers):
x, y, z = data
ax.scatter(x, y, z, alpha=0.4, c=color, edgecolors='none', s=size, marker=mark)
ax.set_xlabel('Residual Sugar')
image.png
散点图2
g = sns.FacetGrid(wines, row='wine_type', col="quality", hue='quality_label', size=4)
g.map(plt.scatter, "residual sugar", "alcohol", alpha=0.5,
edgecolor='k', linewidth=0.5, s=wines['total sulfur dioxide']*2)
fig = g.fig
fig.set_size_inches(18, 8)
fig.subplots_adjust(top=0.85, wspace=0.3)
fig.suptitle('Wine Type - Sulfur Dioxide - Residual Sugar - Alcohol - Quality Class - Quality Rating', fontsize=14)
l = g.add_legend(title='Wine Quality Class')
image.png
