python可視化進階---seaborn1.7 分類資料可視化 - 統計圖 barplot() / countplot() / pointplot()

分類資料可視化 - 統計圖

barplot() / countplot() / pointplot()

1. barplot()

#柱狀圖 - 置信區間估計

#置信區間：樣本均值 + 抽樣誤差

示例1：

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
 
sns.set_context('paper')
 
#加載資料
titanic = sns.load_dataset('titanic')
print(titanic.head())
sns.barplot(x = 'sex', y = 'survived', hue = 'class', data = titanic,
            palette = 'hls',
            order = ['male', 'female'],  #篩選類别
            capsize = 0.05,              #誤差線橫向延申寬度
            saturation = 8,              #顔色飽和度
            errcolor = 'gray', errwidth = 2,  #誤差線顔色、寬度
            ci = 'sd'     #置信區間誤差 --> 0-100内值、 'sd' 、None
            )
#計算資料
print(titanic.groupby(['sex', 'class']).mean()['survived'])
print(titanic.groupby(['sex', 'class']).std()['survived'])      

示例2：

tips = sns.load_dataset('tips')
sns.barplot(x = 'day', y = 'total_bill', hue = 'sex', data = tips,
            palette = 'Blues', edgecolor = 'w')
tips.groupby(['day','sex']).mean()      

示例3:

#加載資料
crashes = sns.load_dataset('car_crashes').sort_values('total', ascending = False)
#建立圖表
f, ax = plt.subplots(figsize = (6,15))
#設定第一個柱狀圖
sns.set_color_codes('pastel')
sns.barplot(x = 'total', y = 'abbrev', data = crashes,
            label = 'Total', color = 'b', edgecolor = 'w')
#設定第二個柱狀圖
sns.set_color_codes('muted')
sns.barplot(x = 'alcohol', y = 'abbrev', data = crashes,
            label = 'Alcohol-involved', color = 'b', edgecolor = 'w')
ax.legend(ncol = 2, loc = 'lower right')
sns.despine(left = True, bottom = True)      

2、countplot()

#計數柱狀圖

#x/y --> 以x或者y軸繪圖（橫向，豎向）

#用法和barplot相似

sns.countplot(x = 'class', hue = 'who', data = titanic, palette = 'magma')      

sns.pointplot(x = 'time', y = 'total_bill', hue = 'smoker', data=tips,
              palette = 'hls',
              dodge = True,  #設定點是否分開
              join = True,   #是否連線
              markers = ['o','x'],linestyles = ['-','--'],#設定點樣式、線型
              )
#計算資料
tips.groupby(['time','smoker']).mean()['total_bill']      

3.pointplot（）

#折線圖 - 置信區間估計