通过使用seaborn缺失数据出现频率的可视化(Visualisation of missing-d

2019-10-28 12:25发布

我想建立一个24x20矩阵(8个部分各自具有60个细胞6×10或),用于通过数据帧熊猫通过在数据集周期(= 480的每个丢失数据出现频率的可视化和绘制它为每个列'A''B' 'C'

到目前为止,我可以映射创建CSV文件,并在矩阵映射正道的值,并通过绘制它sns.heatmap(df.isnull())后改变了丢失数据(NAN&INF)0或类似0.01234这对数据的影响最小,并在另一方面可以被绘制。 下面是我的剧本至今:

import numpy as np
import pandas as pd
import os
import seaborn as sns
import matplotlib.pyplot as plt

def mkdf(ListOf480Numbers):
    normalMatrix = np.array_split(ListOf480Numbers,8)
    fixMatrix = []
    for i in range(8):
        lines = np.array_split(normalMatrix[i],6)
        newMatrix = [0,0,0,0,0,0]
        for j in (1,3,5):
            newMatrix[j] = lines[j]
        for j in (0,2,4):
            newMatrix[j] = lines[j][::-1]
        fixMatrix.append(newMatrix) 
    return fixMatrix

def print_df(fixMatrix):
    values = []
    for i in range(6):
        values.append([*fixMatrix[6][i], *fixMatrix[7][i]])
    for i in range(6):
        values.append([*fixMatrix[4][i], *fixMatrix[5][i]])
    for i in range(6):
        values.append([*fixMatrix[2][i], *fixMatrix[3][i]])
    for i in range(6):
        values.append([*fixMatrix[0][i], *fixMatrix[1][i]])
    df = pd.DataFrame(values)
    return (df)




dft = pd.read_csv('D:\Feryan.TXT', header=None)
id_set = dft[dft.index % 4 == 0].astype('int').values
A = dft[dft.index % 4 == 1].values
B = dft[dft.index % 4 == 2].values
C = dft[dft.index % 4 == 3].values
data = {'A': A[:,0], 'B': B[:,0], 'C': C[:,0]}

df = pd.DataFrame(data, columns=['A','B','C'], index = id_set[:,0])  

nan = np.array(df.isnull())
inf = np.array(df.isnull())
df = df.replace([np.inf, -np.inf], np.nan)
df[np.isinf(df)] = np.nan    # convert inf to nan
#dff = df[df.isnull().any(axis=1)]   # extract sub data frame

#df = df.fillna(0)
#df = df.replace(0,np.nan)



#next iteration create all plots, change the number of cycles
cycles = int(len(df)/480)
print(cycles)
for cycle in range(3):
    count =  '{:04}'.format(cycle)
    j = cycle * 480
    new_value1 = df['A'].iloc[j:j+480]
    new_value2 = df['B'].iloc[j:j+480]
    new_value3 = df['C'].iloc[j:j+480]
    df1 = print_df(mkdf(new_value1))
    df2 = print_df(mkdf(new_value2))
    df3 = print_df(mkdf(new_value3))              
    for i in df:
        try:
            os.mkdir(i)
        except:
            pass
            df1.to_csv(f'{i}/norm{i}{count}.csv', header=None, index=None) 
            df2.to_csv(f'{i}/norm{i}{count}.csv', header=None, index=None)
            df3.to_csv(f'{i}/norm{i}{count}.csv', header=None, index=None)

    #plotting all columns ['A','B','C'] in-one-window side by side


    fig, ax = plt.subplots(nrows=1, ncols=3 , figsize=(20,10))
    plt.subplot(131)

    ax = sns.heatmap(df1.isnull(), cbar=False)
    ax.axhline(y=6, color='w',linewidth=1.5)
    ax.axhline(y=12, color='w',linewidth=1.5)
    ax.axhline(y=18, color='w',linewidth=1.5)
    ax.axvline(x=10, color='w',linewidth=1.5)

    plt.title('Missing-data frequency in A', fontsize=20 , fontweight='bold', color='black', loc='center', style='italic')
    plt.axis('off')

    plt.subplot(132)
    ax = sns.heatmap(df2.isnull(), cbar=False)
    ax.axhline(y=6, color='w',linewidth=1.5)
    ax.axhline(y=12, color='w',linewidth=1.5)
    ax.axhline(y=18, color='w',linewidth=1.5)
    ax.axvline(x=10, color='w',linewidth=1.5)
    plt.title('Missing-data frequency in B', fontsize=20 , fontweight='bold', color='black', loc='center', style='italic')
    plt.axis('off')

    plt.subplot(133)
    ax = sns.heatmap(df3.isnull(), cbar=False)
    ax.axhline(y=6, color='w',linewidth=1.5)
    ax.axhline(y=12, color='w',linewidth=1.5)
    ax.axhline(y=18, color='w',linewidth=1.5)
    ax.axvline(x=10, color='w',linewidth=1.5) 
    plt.title('Missing-data frequency in C', fontsize=20 , fontweight='bold', color='black', loc='center', style='italic')
    plt.axis('off')

    plt.suptitle(f'Missing-data visualization', color='yellow', backgroundcolor='black', fontsize=15, fontweight='bold')
    plt.subplots_adjust(top=0.92, bottom=0.02, left=0.05, right=0.96, hspace=0.2, wspace=0.2)
    fig.text(0.035, 0.93, 'dataset1' , fontsize=19, fontweight='bold', rotation=42., ha='center', va='center',bbox=dict(boxstyle="round",ec=(1., 0.5, 0.5),fc=(1., 0.8, 0.8)))
    #fig.tight_layout()
    plt.savefig(f'{i}/result{count}.png') 
    #plt.show()      

问题是我不知道我怎么能缺少绘制数据出现的频率正确地理解其中的部分和细胞它频繁发生。

注1多个丢失的值的颜色应该是通过周期亮和100%缺失数据应该由白色黑色固体颜色来呈现指示非缺失值。 有可能是从黑色0%至100%的白色条形图开始。

注2我还提供数据集的示例文本文件为3个周期包括几个缺失数据,但它可以被手动修改和增加的: 数据集

预期结果应该是象下面这样:

Answer 1:

你可以存储你的男/ INF数据在一个单独的阵列,你可以在每个楠/ INF周期加起来。

你的阵列似乎总是有相同的大小,所以我有一个固定大小的定义他们。 您可以更改以匹配您的数据:

df1MissingDataFrequency = np.zeros((24,20))

然后你可以把它们加起来,你得到一个nan值(你已经更换infnan在你的代码):

df1MissingDataFrequency = df1MissingDataFrequency + np.isnan(df1).astype(int)

在所有的周期。

你似乎有一些问题,你的缩进。 我不知道这是否是只为你在这里张贴或代码的情况下,如果这是在您的实际代码相同,但此刻你犯了一个新的情节每个周期你redifine df1, df2, df3每个i

有了您丢失的频率数据,你的代码应该是这样的:

import numpy as np
import pandas as pd
import os
import seaborn as sns
import matplotlib.pyplot as plt

def mkdf(ListOf480Numbers):
    normalMatrix = np.array_split(ListOf480Numbers,8)
    fixMatrix = []
    for i in range(8):
        lines = np.array_split(normalMatrix[i],6)
        newMatrix = [0,0,0,0,0,0]
        for j in (1,3,5):
            newMatrix[j] = lines[j]
        for j in (0,2,4):
            newMatrix[j] = lines[j][::-1]
        fixMatrix.append(newMatrix) 
    return fixMatrix

def print_df(fixMatrix):
    values = []
    for i in range(6):
        values.append([*fixMatrix[6][i], *fixMatrix[7][i]])
    for i in range(6):
        values.append([*fixMatrix[4][i], *fixMatrix[5][i]])
    for i in range(6):
        values.append([*fixMatrix[2][i], *fixMatrix[3][i]])
    for i in range(6):
        values.append([*fixMatrix[0][i], *fixMatrix[1][i]])
    df = pd.DataFrame(values)
    return (df)


dft = pd.read_csv('D:/Feryan2.txt', header=None)
id_set = dft[dft.index % 4 == 0].astype('int').values
A = dft[dft.index % 4 == 1].values
B = dft[dft.index % 4 == 2].values
C = dft[dft.index % 4 == 3].values
data = {'A': A[:,0], 'B': B[:,0], 'C': C[:,0]}

df = pd.DataFrame(data, columns=['A','B','C'], index = id_set[:,0])  

nan = np.array(df.isnull())
inf = np.array(df.isnull())
df = df.replace([np.inf, -np.inf], np.nan)
df[np.isinf(df)] = np.nan    # convert inf to nan


df1MissingDataFrequency = np.zeros((24,20))
df2MissingDataFrequency = np.zeros((24,20))
df3MissingDataFrequency = np.zeros((24,20))


#next iteration create all plots, change the number of cycles
cycles = int(len(df)/480)
print(cycles)
for cycle in range(3):
    count =  '{:04}'.format(cycle)
    j = cycle * 480
    new_value1 = df['A'].iloc[j:j+480]
    new_value2 = df['B'].iloc[j:j+480]
    new_value3 = df['C'].iloc[j:j+480]
    df1 = print_df(mkdf(new_value1))
    df2 = print_df(mkdf(new_value2))
    df3 = print_df(mkdf(new_value3))              
    for i in df:
        try:
            os.mkdir(i)
        except:
            pass
    df1.to_csv(f'{i}/norm{i}{count}.csv', header=None, index=None) 
    df2.to_csv(f'{i}/norm{i}{count}.csv', header=None, index=None)
    df3.to_csv(f'{i}/norm{i}{count}.csv', header=None, index=None)

    df1MissingDataFrequency = df1MissingDataFrequency + np.isnan(df1).astype(int)
    df2MissingDataFrequency = df2MissingDataFrequency + np.isnan(df2).astype(int)
    df3MissingDataFrequency = df3MissingDataFrequency + np.isnan(df3).astype(int)

#plotting all columns ['A','B','C'] in-one-window side by side
fig, ax = plt.subplots(nrows=1, ncols=3 , figsize=(10,7))
plt.subplot(131)

ax = sns.heatmap(df1MissingDataFrequency, cbar=False, cmap="gray")
ax.axhline(y=6, color='w',linewidth=1.5)
ax.axhline(y=12, color='w',linewidth=1.5)
ax.axhline(y=18, color='w',linewidth=1.5)
ax.axvline(x=10, color='w',linewidth=1.5)

plt.title('Missing-data frequency in A', fontsize=20 , fontweight='bold', color='black', loc='center', style='italic')
plt.axis('off')

plt.subplot(132)
ax = sns.heatmap(df2MissingDataFrequency, cbar=False, cmap="gray")
ax.axhline(y=6, color='w',linewidth=1.5)
ax.axhline(y=12, color='w',linewidth=1.5)
ax.axhline(y=18, color='w',linewidth=1.5)
ax.axvline(x=10, color='w',linewidth=1.5)
plt.title('Missing-data frequency in B', fontsize=20 , fontweight='bold', color='black', loc='center', style='italic')
plt.axis('off')

plt.subplot(133)
ax = sns.heatmap(df3MissingDataFrequency, cbar=False, cmap="gray")
ax.axhline(y=6, color='w',linewidth=1.5)
ax.axhline(y=12, color='w',linewidth=1.5)
ax.axhline(y=18, color='w',linewidth=1.5)
ax.axvline(x=10, color='w',linewidth=1.5) 
plt.title('Missing-data frequency in C', fontsize=20 , fontweight='bold', color='black', loc='center', style='italic')
plt.axis('off')

plt.suptitle(f'Missing-data visualization', color='yellow', backgroundcolor='black', fontsize=15, fontweight='bold')
plt.subplots_adjust(top=0.92, bottom=0.02, left=0.05, right=0.96, hspace=0.2, wspace=0.2)
fig.text(0.035, 0.93, 'dataset1' , fontsize=19, fontweight='bold', rotation=42., ha='center', va='center',bbox=dict(boxstyle="round",ec=(1., 0.5, 0.5),fc=(1., 0.8, 0.8)))
#fig.tight_layout()
plt.savefig(f'{i}/result{count}.png') 
#plt.show()      

它给你你想要的输出:

编辑

在精神DRY ,我编辑你的代码,所以你没有DF1,DF2,DF3,new_values1,...你复制和遍布粘贴同样的事情。 你已经遍历i ,所以你应该用它来真正解决您的数据帧的三个不同的列:

dft = pd.read_csv('C:/Users/frefra/Downloads/Feryan2.txt', header=None).replace([np.inf, -np.inf], np.nan)
id_set = dft[dft.index % 4 == 0].astype('int').values
A = dft[dft.index % 4 == 1].values
B = dft[dft.index % 4 == 2].values
C = dft[dft.index % 4 == 3].values
data = {'A': A[:,0], 'B': B[:,0], 'C': C[:,0]}
df = pd.DataFrame(data, columns=['A','B','C'], index = id_set[:,0])


new_values = []
dfs = []
nan_frequencies = np.zeros((3,24,20))

#next iteration create all plots, change the number of cycles
cycles = int(len(df)/480)
print(cycles)
for cycle in range(cycles):
    count =  '{:04}'.format(cycle)
    j = cycle * 480
    for idx,i in enumerate(df):
        try:
            os.mkdir(i)
        except:
            pass
        new_value = df[i].iloc[j:j+480]        
        new_values.append(new_value)
        dfi = print_df(mkdf(new_value))
        dfs.append(dfi)
        dfi.to_csv(f'{i}/norm{i}{count}.csv', header=None, index=None) 
        nan_frequencies[idx] = nan_frequencies[idx] + np.isnan(dfi).astype(int)


#plotting all columns ['A','B','C'] in-one-window side by side
fig, ax = plt.subplots(nrows=1, ncols=3 , figsize=(10,7))

for idx,i in enumerate(df):

    plt.subplot(1,3,idx+1)

    ax = sns.heatmap(nan_frequencies[idx], cbar=False, cmap="gray")
    ax.axhline(y=6, color='w',linewidth=1.5)
    ax.axhline(y=12, color='w',linewidth=1.5)
    ax.axhline(y=18, color='w',linewidth=1.5)
    ax.axvline(x=10, color='w',linewidth=1.5)

    plt.title('Missing-data frequency in ' + i, fontsize=20 , fontweight='bold', color='black', loc='center', style='italic')
    plt.axis('off')



文章来源: Visualisation of missing-data occurrence frequency by using seaborn