How do I plot a Distributed Dot Plot using Matplotlib?

Question

I am trying to recreate this scatterplot with my own code: https://www.machinelearningplus.com/wp-content/uploads/2018/11/25_Distributed_Dotplot_Matplotlib-min.png

The code to produce this is: (https://www.machinelearningplus.com/plots/top-50-matplotlib-visualizations-the-master-plots-python/)

# !pip install brewer2mpl
import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
import seaborn as sns
import warnings; warnings.filterwarnings(action='once')

large = 22; med = 16; small = 12
params = {'axes.titlesize': large,
          'legend.fontsize': med,
          'figure.figsize': (16, 10),
          'axes.labelsize': med,
          'axes.titlesize': med,
          'xtick.labelsize': med,
          'ytick.labelsize': med,
          'figure.titlesize': large}
plt.rcParams.update(params)
plt.style.use('seaborn-whitegrid')
sns.set_style("white")
%matplotlib inline

# Version
print(mpl.__version__)  #> 3.0.0
print(sns.__version__)  #> 0.9.0

import matplotlib.patches as mpatches

# Prepare Data
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")
cyl_colors = {4:'tab:red', 5:'tab:green', 6:'tab:blue', 8:'tab:orange'}
df_raw['cyl_color'] = df_raw.cyl.map(cyl_colors)

# Mean and Median city mileage by make
df = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.mean())
df.sort_values('cty', ascending=False, inplace=True)
df.reset_index(inplace=True)
df_median = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.median())

# Draw horizontal lines
fig, ax = plt.subplots(figsize=(16,10), dpi= 80)
ax.hlines(y=df.index, xmin=0, xmax=40, color='gray', alpha=0.5, linewidth=.5, linestyles='dashdot')

# Draw the Dots
for i, make in enumerate(df.manufacturer):
    df_make = df_raw.loc[df_raw.manufacturer==make, :]
    ax.scatter(y=np.repeat(i, df_make.shape[0]), x='cty', data=df_make, s=75, edgecolors='gray', c='w', alpha=0.5)
    ax.scatter(y=i, x='cty', data=df_median.loc[df_median.index==make, :], s=75, c='firebrick')

# Annotate    
ax.text(33, 13, "$red \; dots \; are \; the \: median$", fontdict={'size':12}, color='firebrick')

# Decorations
red_patch = plt.plot([],[], marker="o", ms=10, ls="", mec=None, color='firebrick', label="Median")
plt.legend(handles=red_patch)
ax.set_title('Distribution of City Mileage by Make', fontdict={'size':22})
ax.set_xlabel('Miles Per Gallon (City)', alpha=0.7)
ax.set_yticks(df.index)
ax.set_yticklabels(df.manufacturer.str.title(), fontdict={'horizontalalignment': 'right'}, alpha=0.7)
ax.set_xlim(1, 40)
plt.xticks(alpha=0.7)
plt.gca().spines["top"].set_visible(False)    
plt.gca().spines["bottom"].set_visible(False)    
plt.gca().spines["right"].set_visible(False)    
plt.gca().spines["left"].set_visible(False)   
plt.grid(axis='both', alpha=.4, linewidth=.1)
plt.show()

Однако всякий раз, когда я пытаюсь запустить этот код, я получаю ValueError: истинное значение массива с более чем одним элементом неоднозначно. Используйте a.any() или a.all()

Итак, я добавил.any () к y=np.repeat(i, df_make.shape[0]) и перезапустил

И теперь я получаю ValueError: x и y должны быть одного размера

Просто из googling я понимаю, что каким-то образом x и y имеют разные размеры, но я не уверен, как это исправить и заставить его работать, чтобы затем я мог применить его к своим собственным данным.

Спасибо!

Answer 1

Вероятно, ошибка вызвана тем, что первая буква "y" - это массив, а не список.

ax.scatter(y=[i]*df_make.shape[0], ...)

полный код ：

import matplotlib.patches as mpatches

# Prepare Data
df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")
cyl_colors = {4:'tab:red', 5:'tab:green', 6:'tab:blue', 8:'tab:orange'}
df_raw['cyl_color'] = df_raw.cyl.map(cyl_colors)

# Mean and Median city mileage by make
df = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.mean())
df.sort_values('cty', ascending=False, inplace=True)
df.reset_index(inplace=True)
df_median = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.median())

# Draw horizontal lines
fig, ax = plt.subplots(figsize=(16,10), dpi= 80)
ax.hlines(y=df.index, xmin=0, xmax=40, color='gray', alpha=0.5, linewidth=.5, linestyles='dashdot')

# Draw the Dots
for i, make in enumerate(df.manufacturer):
    df_make = df_raw.loc[df_raw.manufacturer==make, :]
    ax.scatter(y=[i]*df_make.shape[0], x='cty', data=df_make, s=75, edgecolors='gray', c='w', alpha=0.5)
    ax.scatter(y=i, x='cty', data=df_median.loc[df_median.index==make, :], s=75, c='firebrick')
    
# Annotate    
ax.text(33, 13, "$red \; dots \; are \; the \: median$", fontdict={'size':12}, color='firebrick')

# Decorations
red_patch = plt.plot([],[], marker="o", ms=10, ls="", mec=None, color='firebrick', label="Median")
plt.legend(handles=red_patch)
ax.set_title('Distribution of City Mileage by Make', fontdict={'size':22})
ax.set_xlabel('Miles Per Gallon (City)', alpha=0.7)
ax.set_yticks(df.index)
ax.set_yticklabels(df.manufacturer.str.title(), fontdict={'horizontalalignment': 'right'}, alpha=0.7)
ax.set_xlim(1, 40)
plt.xticks(alpha=0.7)
plt.gca().spines["top"].set_visible(False)    
plt.gca().spines["bottom"].set_visible(False)    
plt.gca().spines["right"].set_visible(False)    
plt.gca().spines["left"].set_visible(False)   
plt.grid(axis='both', alpha=.4, linewidth=.1)
plt.show()

ht tps:https://stackru.com/images/8701b723760400cc2a72fd84a99fb3681c476ac4.png