0

我想创建一个 24x20 矩阵（8 个部分，每个部分有 60 个单元格或 6x10），用于通过 panda 数据框在数据集中通过周期（=每个480 个值）可视化缺失数据出现的频率，并为每一列绘制它，，.'A''B''C'

到目前为止，我可以映射创建的 csv 文件并在矩阵中以正确的方式映射值，并sns.heatmap(df.isnull())在将缺失数据（nan & inf）更改为对数据影响最小的0东西或类似0.01234的东西后绘制它，另一方面可以被绘制。以下是我到目前为止的脚本：

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()

问题是我不知道如何正确绘制缺失数据发生的频率以了解它经常发生在哪些部分和单元格中。

注1缺失值越多，颜色越亮，循环中 100% 的缺失数据应以白色表示，纯黑色表示非缺失值。可能有一个从黑色 0% 到 100% 白色的条形图。

注2我还提供了 3 个周期的数据集示例文本文件，包括少量缺失数据，但可以手动修改和增加：数据集

预期结果应如下所示：

图像

4

1 回答 1

1

您可以将您的 nan/inf 数据存储在一个单独的数组中，您可以将每个 nan/inf 的周期累加起来。

您的数组似乎总是具有相同的大小，因此我将它们定义为固定大小。您可以更改它以匹配您的数据：

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

然后你可以将它们添加到你得到一个nan值的地方（你已经在你的代码中替换了）inf：nan

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

在你所有的周期。

您的缩进似乎有一些问题。我不知道这是否仅适用于您在此处发布的代码，或者在您的实际代码中是否相同，但目前您在每个周期制作一个新图并为df1, df2, df3每个i.

由于缺少频率数据，您的代码应如下所示：

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()

这为您提供了所需的输出：

南频

编辑

本着DRY的精神，我编辑了你的代码，所以你没有 df1, df2, df3, new_values1, ... 你复制和粘贴相同的东西。您已经循环了i，因此您应该使用它来实际处理数据框中的三个不同列：

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')
于 2019-02-04T12:57:48.927 回答