Python 如何从具有权重的数据创建箱线图？

我有以下数据：

姓名

姓名出现的次数（

计数

），以及每个姓名的

得分

。我想创建一个包含

得分

的方框和胡须图，通过其

计数对每个名字的
得分
进行加权

结果应该是相同的，如果我有原始（不是频率）形式的数据。但我不想将数据转换成这样的形式，因为它的大小会迅速膨胀

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

data = {
    "Name":['Sara', 'John', 'Mark', 'Peter', 'Kate'],
    "Count":[20, 10, 5, 2, 5], 
    "Score": [2, 4, 7, 8, 7]
}
df = pd.DataFrame(data)
print(df)

我不知道如何在Python中解决这个问题。感谢您的帮助
 这里有两种回答这个问题的方法。您可能会想到第一个，但是它不是一个好的解决方案，因为在计算中位数的置信区间时，它有下面的代码，使用示例数据，参考
matplotlib/cbook/_init\u uuuuuu.py
。因此，与其他定制代码相比，第二种代码比其他任何代码都要好，因为它经过了良好的测试

def boxplot_stats(X, whis=1.5, bootstrap=None, labels=None,
                  autorange=False):
    def _bootstrap_median(data, N=5000):
        # determine 95% confidence intervals of the median
        M = len(data)
        percentiles = [2.5, 97.5]

        bs_index = np.random.randint(M, size=(N, M))
        bsData = data[bs_index]
        estimate = np.median(bsData, axis=1, overwrite_input=True)

第一名：

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np

data = {
    "Name": ['Sara', 'John', 'Mark', 'Peter', 'Kate'],
    "Count": [20, 10, 5, 2, 5],
    "Score": [2, 4, 7, 8, 7]
}

df = pd.DataFrame(data)
print(df)


def boxplot(values, freqs):
    values = np.array(values)
    freqs = np.array(freqs)
    arg_sorted = np.argsort(values)
    values = values[arg_sorted]
    freqs = freqs[arg_sorted]
    count = freqs.sum()
    fx = values * freqs
    mean = fx.sum() / count
    variance = ((freqs * values ** 2).sum() / count) - mean ** 2
    variance = count / (count - 1) * variance  # dof correction for sample variance
    std = np.sqrt(variance)
    minimum = np.min(values)
    maximum = np.max(values)
    cumcount = np.cumsum(freqs)

    print([std, variance])
    Q1 = values[np.searchsorted(cumcount, 0.25 * count)]
    Q2 = values[np.searchsorted(cumcount, 0.50 * count)]
    Q3 = values[np.searchsorted(cumcount, 0.75 * count)]

    '''
    interquartile range (IQR), also called the midspread or middle 50%, or technically
    H-spread, is a measure of statistical dispersion, being equal to the difference
    between 75th and 25th percentiles, or between upper and lower quartiles,[1][2]
    IQR = Q3 −  Q1. In other words, the IQR is the first quartile subtracted from
    the third quartile; these quartiles can be clearly seen on a box plot on the data.
    It is a trimmed estimator, defined as the 25% trimmed range, and is a commonly used
    robust measure of scale.
    '''

    IQR = Q3 - Q1

    '''
    The whiskers add 1.5 times the IQR to the 75 percentile (aka Q3) and subtract
    1.5 times the IQR from the 25 percentile (aka Q1).  The whiskers should include
    99.3% of the data if from a normal distribution.  So the 6 foot tall man from
    the example would be inside the whisker but my 6 foot 2 inch girlfriend would
    be at the top whisker or pass it.
    '''
    whishi = Q3 + 1.5 * IQR
    whislo = Q1 - 1.5 * IQR

    stats = [{
        'label': 'Scores',  # tick label for the boxplot
        'mean': mean,  # arithmetic mean value
        'iqr': Q3 - Q1,  # 5.0,
#         'cilo': 2.0,  # lower notch around the median
#         'cihi': 4.0,  # upper notch around the median
        'whishi': maximum,  # end of the upper whisker
        'whislo': minimum,  # end of the lower whisker
        'fliers': [],  # '\array([], dtype=int64)',  # outliers
        'q1': Q1,  # first quartile (25th percentile)
        'med': Q2,  # 50th percentile
        'q3': Q3  # third quartile (75th percentile)
    }]

    fs = 10  # fontsize
    _, axes = plt.subplots(nrows=1, ncols=1, figsize=(6, 6), sharey=True)
    axes.bxp(stats)
    axes.set_title('Default', fontsize=fs)
    plt.show()


boxplot(df['Score'], df['Count'])


import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt


data = {
    "Name": ['Sara', 'John', 'Mark', 'Peter', 'Kate'],
    "Count": [20, 10, 5, 2, 5],
    "Score": [2, 4, 7, 8, 7]
}

df = pd.DataFrame(data)
print(df)

labels = ['Scores']

data = df['Score'].repeat(df['Count']).tolist()

# compute the boxplot stats
stats = cbook.boxplot_stats(data, labels=labels, bootstrap=10000)

print(['stats :', stats])

fs = 10  # fontsize

fig, axes = plt.subplots(nrows=1, ncols=1, figsize=(6, 6), sharey=True)
axes.bxp(stats)
axes.set_title('Boxplot', fontsize=fs)

plt.show()

秒：

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np

data = {
    "Name": ['Sara', 'John', 'Mark', 'Peter', 'Kate'],
    "Count": [20, 10, 5, 2, 5],
    "Score": [2, 4, 7, 8, 7]
}

df = pd.DataFrame(data)
print(df)


def boxplot(values, freqs):
    values = np.array(values)
    freqs = np.array(freqs)
    arg_sorted = np.argsort(values)
    values = values[arg_sorted]
    freqs = freqs[arg_sorted]
    count = freqs.sum()
    fx = values * freqs
    mean = fx.sum() / count
    variance = ((freqs * values ** 2).sum() / count) - mean ** 2
    variance = count / (count - 1) * variance  # dof correction for sample variance
    std = np.sqrt(variance)
    minimum = np.min(values)
    maximum = np.max(values)
    cumcount = np.cumsum(freqs)

    print([std, variance])
    Q1 = values[np.searchsorted(cumcount, 0.25 * count)]
    Q2 = values[np.searchsorted(cumcount, 0.50 * count)]
    Q3 = values[np.searchsorted(cumcount, 0.75 * count)]

    '''
    interquartile range (IQR), also called the midspread or middle 50%, or technically
    H-spread, is a measure of statistical dispersion, being equal to the difference
    between 75th and 25th percentiles, or between upper and lower quartiles,[1][2]
    IQR = Q3 −  Q1. In other words, the IQR is the first quartile subtracted from
    the third quartile; these quartiles can be clearly seen on a box plot on the data.
    It is a trimmed estimator, defined as the 25% trimmed range, and is a commonly used
    robust measure of scale.
    '''

    IQR = Q3 - Q1

    '''
    The whiskers add 1.5 times the IQR to the 75 percentile (aka Q3) and subtract
    1.5 times the IQR from the 25 percentile (aka Q1).  The whiskers should include
    99.3% of the data if from a normal distribution.  So the 6 foot tall man from
    the example would be inside the whisker but my 6 foot 2 inch girlfriend would
    be at the top whisker or pass it.
    '''
    whishi = Q3 + 1.5 * IQR
    whislo = Q1 - 1.5 * IQR

    stats = [{
        'label': 'Scores',  # tick label for the boxplot
        'mean': mean,  # arithmetic mean value
        'iqr': Q3 - Q1,  # 5.0,
#         'cilo': 2.0,  # lower notch around the median
#         'cihi': 4.0,  # upper notch around the median
        'whishi': maximum,  # end of the upper whisker
        'whislo': minimum,  # end of the lower whisker
        'fliers': [],  # '\array([], dtype=int64)',  # outliers
        'q1': Q1,  # first quartile (25th percentile)
        'med': Q2,  # 50th percentile
        'q3': Q3  # third quartile (75th percentile)
    }]

    fs = 10  # fontsize
    _, axes = plt.subplots(nrows=1, ncols=1, figsize=(6, 6), sharey=True)
    axes.bxp(stats)
    axes.set_title('Default', fontsize=fs)
    plt.show()


boxplot(df['Score'], df['Count'])


import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt


data = {
    "Name": ['Sara', 'John', 'Mark', 'Peter', 'Kate'],
    "Count": [20, 10, 5, 2, 5],
    "Score": [2, 4, 7, 8, 7]
}

df = pd.DataFrame(data)
print(df)

labels = ['Scores']

data = df['Score'].repeat(df['Count']).tolist()

# compute the boxplot stats
stats = cbook.boxplot_stats(data, labels=labels, bootstrap=10000)

print(['stats :', stats])

fs = 10  # fontsize

fig, axes = plt.subplots(nrows=1, ncols=1, figsize=(6, 6), sharey=True)
axes.bxp(stats)
axes.set_title('Boxplot', fontsize=fs)

plt.show()

参考资料：




这个问题提得太晚了，但万一有人遇到它，它会很有用--

当权重为整数时，可以使用reindex按计数展开，然后直接使用箱线图调用。我已经能够在数据帧上实现这一点，其中数千个数据帧变成了几十万个数据帧，而没有内存挑战，特别是如果实际重新索引的数据帧被包装到第二个函数中，而该函数不在内存中分配它

import pandas as pd
import seaborn as sns

data = {
    "Name": ['Sara', 'John', 'Mark', 'Peter', 'Kate'],
    "Count": [20, 10, 5, 2, 5],
    "Score": [2, 4, 7, 8, 7]
}
df = pd.DataFrame(data)

def reindex_df(df, weight_col):
    """expand the dataframe to prepare for resampling
    result is 1 row per count per sample"""
    df = df.reindex(df.index.repeat(df[weight_col]))
    df.reset_index(drop=True, inplace=True)
    return(df)

df = reindex_df(df, weight_col = 'Count')

sns.boxplot(x='Name', y='Score', data=df)

或者如果你关心记忆

def weighted_boxplot(df, weight_col):
    sns.boxplot(x='Name', 
                y='Score', 
                data=reindex_df(df, weight_col = weight_col))
    
weighted_boxplot(df, 'Count')

有趣。事实上，我对举重还不熟悉。这本质上就是传递权重数组所做的吗？@WhiteTie在
sns.boxplot（…
）后面添加了
print（df）
，以帮助您理解数据框。@WhiteTie数据框将数据保存在python字典中。如果您查看源代码
类数据框（NDFrame）：
在
pandas/core/frame.py
中，你会得到它。编辑：我的意思是我想要一个方框图，不是在名称级别，而是在聚合级别——一个显示平均值、中值、Q25等的方框和胡须图。换句话说，我想要汇总整个数据。这显示了一个不同的东西。例如，这将得到所需的平均值。仍然不确定h如何从中创建箱线图：
desired_mean=sum（（df['Count']*df['Score']）/sum（df['Count']）