Python seaborn matplotlib 对数据进行图表分析

我会带着你远行 2021-06-10 20:42 839阅读 0赞

[matplotlib官网][matplotlib]  
[基于matplotlib的seaborn官网][matplotlib_seaborn]

import seaborn as sns
    import matplotlib.pyplot as plt
    %matplotlib inline # notebook使用

import seaborn as sns  
    sns.set_style("whitegrid") 
    # 设置主题，可选项有darkgrid , whitegrid , dark , white ,和 ticks 
    sns.set(style="dark", palette="muted", color_codes=True)    
    # 通过参数设置主题

## **一、plt.hist** ##

g = sns.FacetGrid(train_data, col='Survived')
    # col,row,hue参数用于定义绘制数据的子集。由于survived有两个参数，会有两个图
    g.map(plt.hist, 'Age', bins=20)
    # hist直方图， ‘Age’为横坐标， bins绘制的直方数量
    plt.show() #左图为在Survived=0的子集内，Age和数量的分布图。

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzI3MTkzNzMzNTcx]

grid = sns.FacetGrid(train_data, hue='Survived')
    # hue参数的把两个直方图画在同一张图上，其中有size参数决定高度，aspect长宽比，width=size*aspect
    grid.map(plt.hist, 'Age', alpha=0.5, bins=20)
    grid.add_legend()
    # 将hue标签显示在图上
    plt.show()

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzI3MjAzMDQxNjI2]

#inter1_num为数值数组
    plt.hist(inter1_num)

#对字符串数组画直方图
    import pandas
    from collections import Counter
    a = ['a', 'a', 'a', 'a', 'b', 'b', 'c', 'c', 'c', 'd', 'e', 'e', 'e', 'e', 'e']
    letter_counts = Counter(a)
    df = pandas.DataFrame.from_dict(letter_counts, orient='index')
    df.plot(kind='bar')

## **二、pointplot** ##

显示数据的均值和偏差

grid = sns.FacetGrid(train_data, row='Embarked', size=2.2, aspect=1.6)
    grid.map(sns.pointplot, 'Pclass', 'Survived', 'Sex', palette='deep')
    # map函数将grid的子集应用于pointplot函数，其后面参数是pointplot的参数，分别为横坐标，纵坐标，hue。palette是调色板折线的颜色。
    grid.add_legend()
    plt.show()

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzI3MjA1NzMxNzgz]

sns.pointplot(x="Pclass", y="Survived", hue="Sex", data=data_train,palette={"male": "blue", "female": "pink"},markers=["*", "o"], linestyles=["-", "--"]);

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODAxMTQzNTE5MDAy]

import pandas as pd
    import seaborn as sns
    import matplotlib.ticker as ticker
    
    name = '5.csv'
    size = 15
    linewidth = 1
    marker_size = 40
    
    plt.rcParams["axes.labelsize"] = size  # label大小
    plt.rcParams["lines.linewidth"] = linewidth  # line大小
    fig,a = plt.subplots(figsize=(10,4))
    data = pd.read_csv(name)
    data = data[data['epoch']<71]
    ax = sns.pointplot(x="epoch", y="test-accuracy", hue="method", data=data,
                  palette="deep",dodge=True, scale=0.5, markers=["o", "x", "^", "<"]);
    ax.xaxis.set_major_locator(ticker.MultipleLocator(10)) #控制x轴单元距离
    ax.xaxis.set_major_formatter(ticker.ScalarFormatter())
    ax.set(ylim=(70,95))
    plt.gca().legend().set_title('') #除掉legend标题
    # plt.setp(ax.get_legend().get_texts(), fontsize=size) # 设置legend大小
    
    for lh in plt.legend(fontsize=size).legendHandles:           # 设置marker大小
        lh.set_sizes([marker_size+20])
    plt.setp(ax.collections, sizes=[marker_size])  # 设置legend marker大小
    ax.tick_params(labelsize=size)  # 设置tick大小
    # plt.ylabel('train-accuracy (%)')
    ax.set(xlabel='迭代次数', ylabel='正确率/%')
    plt.show()
    
    fig.savefig(name+'.svg', format='svg', dpi=1200, bbox_inches='tight')

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE2MjM0NjEz_size_16_color_FFFFFF_t_70]

import matplotlib
    matplotlib.use('Agg')
    # mpl.rcParams['figure.dpi'] = 600
    import matplotlib.pyplot as plt
    
    %matplotlib inline
    plt.style.use('seaborn-bright')
    plt.rcParams['font.family'] = 'Times New Roman'
    plt.rcParams['figure.figsize'] = 8, 8
    # plt.rcParams['xtick.labelsize'] = 24
    # plt.rcParams['ytick.labelsize'] = 24
    
    tick_label_size = 14
    label_size = 14
    
    data_name = datatv
    x_axis = [10, 72, 134, 196, 258, 320]
    line1 = [0.8239, 
    0.8315, 
    0.8394, 
    0.8350, #-0.8374-0.8372
    0.8414, 
    0.8418, 
    ]
    line2 = [0.8211-0.006,
    0.8168,
    0.8218,
    0.8143, #-0.8178
    0.8177,
    0.8171,
    ]
    line3 = [0.8416,
    0.8513,
    0.8534,
    0.8495, #-0.8520-0.8548
    0.8536,
    0.8567,
    ]
    line4 = [0.8343,
    0.8359,
    0.8384,
    0.8374, #-0.8392
    0.8384,
    0.8452,
    ]
    
    xlim = (4, 326)
    xticks = [10, 72, 134, 196, 258, 320]
    xtickslabel = [10, 20, 40, 80, 160, 320]
    xlabel = 'Number of hiddeng units'
    
    ylim = (0.813, 0.858)
    yticks = [0.82,0.83, 0.84, 0.85,]
    ytickslabel = [0.82,0.83, 0.84, 0.85,  ]
    ylabel = 'AUC(test)'
    
    
    fig, ax = plt.subplots(1, 1)
    ax.grid(color='gray', linestyle='--', linewidth=1, alpha=0.3)  
    ax.set_facecolor('white')
    ax.set_title(data_name)
    # fig.suptitle(datael, fontsize=label_size)
    
    ax.set_xlim(xlim[0], xlim[1])
    ax.set_xticks(xticks)
    ax.set_xticklabels(xtickslabel, fontsize=tick_label_size)
    ax.set_xlabel(xlabel, fontsize=label_size)
    
    ax.set_ylim(ylim)
    ax.set_yticks(yticks)
    ax.set_yticklabels(ytickslabel, fontsize=tick_label_size)
    ax.set_ylabel(ylabel, fontsize=label_size)
    
    ax.plot(x_axis, line1, 'bs--', markersize=9, linewidth=2, label=dcin_col)
    ax.plot(x_axis, line2, 'g^--', markersize=10, linewidth=2, label=dcin_smi)
    ax.plot(x_axis, line3, 'ro--', markersize=9, linewidth=2, label=dcin_col_app)
    # ax.plot(x_axis, line4, 'cv--', markersize=10, linewidth=2, label=dcin_smi_app)
    
    plt.legend(bbox_to_anchor=(0.89, 0.40), borderaxespad=0., fontsize=label_size, fancybox=False)
    # plt.tight_layout(w_pad=-8)
    # plt.savefig('test.jpg', bbox_inches='tight', dpi=200)

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE2MjM0NjEz_size_16_color_FFFFFF_t_70 1]

## **三、barplot** ##

显示数据的均值和偏差

grid = sns.FacetGrid(train_data, col='Embarked', hue='Survived', palette={0: 'k', 1: 'w'})
    grid.map(sns.barplot, 'Sex', 'Fare', alpha=.5)
    #ci=sd表示用竖线显示标准偏差，=None不显示
    grid.add_legend()
    plt.show()

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzI3MjEzMTA3OTEw]

## **四、pairplot：** ##

查看数据相关性。

_ = sns.pairplot(df[:50], vars=[8, 11, 12, 14, 19], hue="class", size=1.5)
    # vars需绘制的列名，hue使用的是二分类的标记
    # diag_kind="kde"能将对角线图换成kde

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzMxMTYwNTI0NzEz]  
图中可以看出特征11和特征14几乎将分类目标class的分布线分了。而特质12和特征19负相关，特征14与特征19强相关，注意对有些模型（朴素贝叶斯分类器假设特征独立）会有影响。

## **五、corrplot：** ##

主要用于分析特征的两两相关。

sns.pairplot(iris)

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzMxMTYyNjMyMDk4]  
对角线为特征，左下角为相关性热点图，有上角为相关系数。

## **六、heatmap** ##

主要用于分析特征的两两相关。

colormap = plt.cm.viridis
    plt.figure(figsize=(12,12))
    plt.title('Pearson Correlation of Features', y=1.05, size=15)
    sns.heatmap(train.astype(float).corr(),linewidths=0.1,vmax=1.0, square=True, cmap=colormap, linecolor='white', annot=True)
    # linewidths，linecolor划分线的宽度和颜色，annot是否在方格里注释数据，vmin, vmax相关度最大值和最小值，此处限制1.0最大，可见图中图谱最大为1.0

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODAxMTYzNTEzODg5]

## **七、jointplot,scatter** ##

查看数据分布和离群点

sns.jointplot(x="SepalLengthCm", y="SepalWidthCm", data=iris, size=5)

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTUzNzQzNTgy]  
为了看到分类目标，使用:

sns.FacetGrid(iris, hue="Species", size=5) \
       .map(plt.scatter, "SepalLengthCm", "SepalWidthCm") \
       .add_legend()

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTUzOTA5Mjc4]

# 可用于查看分布，离散点
    plt.scatter(range(mergepred.shape[0]), np.sort(mergepred), color="red")

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE2MjM0NjEz_size_16_color_FFFFFF_t_70 2]

## **八、boxplot** ##

分析单一特征。

sns.boxplot(x="Species", y="PetalLengthCm", data=iris)

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTU0MTM5ODI4]

ax = sns.boxplot(x="Species", y="PetalLengthCm", data=iris)
    ax = sns.stripplot(x="Species", y="PetalLengthCm", data=iris, jitter=True, edgecolor="gray")
    # jitter不让点分布在一条垂直线上

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTU0NTQ0MzQ0]

## **九、violinplot** ##

类似于boxplot，分析单一变量。

sns.violinplot(x="Species", y="PetalLengthCm", data=iris, size=6)

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTU1MDMyMDUw]

## **十、kdeplot(核密度估计图)** ##

分析单一变量。

sns.FacetGrid(iris, hue="Species", size=6) \
       .map(sns.kdeplot, "PetalLengthCm") \
       .add_legend()

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTU1OTQ2MjAw]

#直方图+核密度估计图
        sns.distplot(inter1_num)
        sns.distplot(Einter1_num)
        plt.show()
        #二维核密度估计图
        sns.kdeplot(inter1_num,Einter1_num,shade=True)
        plt.show()

![在这里插入图片描述][70]

## **十一、pandas画图** ##

# Andrews Curves involve using attributes of samples as coefficients for Fourier series
    # and then plotting these
    from pandas.tools.plotting import andrews_curves
    andrews_curves(iris.drop("Id", axis=1), "Species")

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTYxMTM3NDgw]

# 将特征作为横坐标，绘制每个样例取值
    from pandas.tools.plotting import parallel_coordinates
    parallel_coordinates(iris.drop("Id", axis=1), "Species")

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTYxMjE5NTA5]

将特征作为一个点绘制，通过相对权值将样例绘制成点。
    from pandas.tools.plotting import radviz
    radviz(iris.drop("Id", axis=1), "Species")

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTYxMzAxMDk0]

## **十二、WordCloud云图** ##

用于分析文本中word出现的频率，越高，显示越大。

clean_mask=np.array(Image.open("../input/imagesforkernal/safe-zone.png"))
    clean_mask=clean_mask[:,:,1]
    #wordcloud for clean comments
    subset=train[train.clean==True]
    text=subset.comment_text.values
    wc= WordCloud(background_color="black",max_words=2000,mask=clean_mask,stopwords=stopword)
    wc.generate(" ".join(text))
    plt.figure(figsize=(20,10))
    plt.axis("off")
    plt.title("Words frequented in Clean Comments", fontsize=20)
    plt.imshow(wc.recolor(colormap= 'viridis' , random_state=17), alpha=0.98)
    plt.show()

![这里写图片描述][aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTgwMzA2MTYzODMwNjgy]

## **十三、折线图** ##

plt.plot(inter1_num)

## **十四、画上文字，多张图** ##

def showimg(im1,im2,match_rate):
        plt.figure(figsize=(5, 1))  # 设置图像大小
        plt.subplot(1, 3, 1)  # 在1*3图格的第1格画上下面图片
        plt.imshow(cv2.imread(im1)[: , : , : : -1])
        plt.subplot(1, 3, 2) # 在1*3图格的第2格画上下面图片
        plt.text(0.5, 0.5, match_rate, ha='center', va='center',) #画上文字
        plt.setp(plt.gca(), frame_on=False, xticks=(), yticks=()) #除去外框
        plt.subplot(1, 3, 3) # 在1*3图格的第3格画上下面图片
        plt.imshow(cv2.imread(im2)[: , : , : : -1])
        plt.show() # 显示

![在这里插入图片描述][70 1]

for qunum in range(500):
    #     if random.random()>0.5:
    #         continue
        scores, indexes = tree.kneighbors([query_fea[qunum]])
        scores, indexes = scores[0][::-1], indexes[0][::-1]
        print("query", query_cut[qunum])
        plt.figure(figsize=(20, 20))
        for ind, score in enumerate(scores):
            im = Image.open(image_dir+image_files[indexes[ind]]).resize((240,240))
            plt.subplot(1, 5, ind+1)
            plt.title(str(indexes[ind]) +"——"+ str(score))
            plt.imshow(im)
        plt.show()
        print()

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE2MjM0NjEz_size_16_color_FFFFFF_t_70 3]

## 十五、venn图 ##

from matplotlib_venn import venn2,venn2_circles,venn3,venn3_circles
    from matplotlib_venn import venn3_unweighted

venn3([label_set, image_set, text_set], ("label", "cnn", "bert"))
    
    venn3_unweighted([merge_set, image_set, text_set], ("merge", "cnn", "bert"))
    
    c = venn3_circles([merge_set, image_set, text_set], linewidth=1)
    c[0].set_edgecolor('red')
    c[1].set_edgecolor('blue')
    c[1].set_edgecolor('green')

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE2MjM0NjEz_size_16_color_FFFFFF_t_70 4]

## 十六 目标检测BBOX绘制 ##

import matplotlib.pyplot as plt
    import matplotlib.patches as pt 
     
        num = 0
        for img_id,item in bbox.items():
            num += 1
            if(num>10):
                continue
            fig, ax = plt.subplots(1)
            img =  plt.imread(test_dir+img_dict[img_id])
            plt.imshow(img)
            for bb in item:
                xy = (bb["bbox"][0],bb["bbox"][1])
                p = pt.Rectangle(xy, bb["bbox"][2], bb["bbox"][3], fill=False, edgecolor = 'red',linewidth=1)
                ax.add_patch(p)
                ax.text(xy[0], xy[1],str(round(bb["score"],2))+"—"+str(bb["category_id"]),color="red")
            plt.show()

[matplotlib]: http://matplotlib.org/gallery.html
[matplotlib_seaborn]: http://seaborn.pydata.org/
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzI3MTkzNzMzNTcx]: /images/20210520/c958dfaa30c541c791a431de09cbb259.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzI3MjAzMDQxNjI2]: /images/20210520/b9d08bd560e549f2822ae27dd3860a8a.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzI3MjA1NzMxNzgz]: /images/20210520/997aa81d06cb41e5aae0fe8b885d1022.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODAxMTQzNTE5MDAy]: /images/20210520/fa8537c83f164384b03c74bc9e817079.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE2MjM0NjEz_size_16_color_FFFFFF_t_70]: /images/20210520/c83e733732284626a0d4e46bb6fae827.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE2MjM0NjEz_size_16_color_FFFFFF_t_70 1]: /images/20210520/4c9b1063d7b946b09f8f6be78ea93e32.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzI3MjEzMTA3OTEw]: /images/20210520/c2348c89ab5144b8aad553f958884960.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzMxMTYwNTI0NzEz]: /images/20210520/ba302f0ae2074f4a9f073082da834f74.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwNzMxMTYyNjMyMDk4]: /images/20210520/c4fa06a0cb184cf8bb5e47013a2488fc.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODAxMTYzNTEzODg5]: /images/20210520/f27a304d81d24d1cb3e6d719439fe0a7.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTUzNzQzNTgy]: /images/20210520/e8556006ae8941c998a9f9e0b76fb36c.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTUzOTA5Mjc4]: /images/20210520/6d7e38f45c724e2890d175f9011551cb.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE2MjM0NjEz_size_16_color_FFFFFF_t_70 2]: /images/20210520/8a26a964e97046e0824db0b222b871ba.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTU0MTM5ODI4]: /images/20210520/dafd909a0c2143c38b61f1f04ea686b7.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTU0NTQ0MzQ0]: /images/20210520/d273850222644f6196dbbe2eb92a6457.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTU1MDMyMDUw]: /images/20210520/3528cb77d8064c8cb1d03a95639fb4ec.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTU1OTQ2MjAw]: /images/20210520/bb4fbc0a959d430587c6ba9a2c2a7ba0.png
[70]: /images/20210520/5ee2afbfce5b4d34a9ab2bb1101cebed.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTYxMTM3NDgw]: /images/20210520/f0ab212dd60a4b1384bf01a0505f9ed6.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTYxMjE5NTA5]: /images/20210520/484223d09533428ba08d7fc1fea8fefa.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTcwODA0MTYxMzAxMDk0]: /images/20210520/7624d40c8b424536be7d99bef2e31d32.png
[aHR0cDovL2ltZy5ibG9nLmNzZG4ubmV0LzIwMTgwMzA2MTYzODMwNjgy]: /images/20210520/54658698c5b34c1da8e861e2604bb368.png
[70 1]: /images/20210520/678d633618564b3d8f89ad65628c50a3.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE2MjM0NjEz_size_16_color_FFFFFF_t_70 3]: /images/20210520/d36a7d60bf344cc0b09430aa4efb79ca.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzE2MjM0NjEz_size_16_color_FFFFFF_t_70 4]: /images/20210520/b8838aae9b564f3688d09306c0818b34.png