熬夜整理的资料：分享Python数据可视化图表代码和案例给大家

前言

本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,版权归原作者所有,如有问题请及时联系我们以作处理。

闲话不多说，直接上干货

1华夫饼图

waffle可以使用该pywaffle软件包创建该图表，并用于显示较大人群中各组的组成。

#! pip install pywaffle
# reference: https://*.com/questions/41400136/how-to-do-waffle-charts-in-python-square-piechart
from pywaffle import waffle

# import 
df_raw = pd.read_csv("data/mpg_ggplot2.csv")

# prepare data
df = df_raw.groupby('class').size().reset_index(name='counts')
n_categories = df.shape[0]
colors = [plt.cm.inferno_r(i/float(n_categories)) for i in range(n_categories)]

# draw plot and decorate
fig = plt.figure(
    figureclass=waffle,
    plots={
        '111': {
            'values': df['counts'],
            'labels': ["{0} ({1})".format(n[0], n[1]) for n in df[['class', 'counts']].itertuples()],
            'legend': {'loc': 'upper left', 'bbox_to_anchor': (1.05, 1), 'fontsize': 12},
            'title': {'label': '# vehicles by class', 'loc': 'center', 'fontsize':18}
        },
    },
    rows=7,
    colors=colors,
    figsize=(16, 9)
)

 

 

 

#! pip install pywaffle
from pywaffle import waffle

# import
# df_raw = pd.read_csv("data/mpg_ggplot2.csv")

# prepare data
# by class data
df_class = df_raw.groupby('class').size().reset_index(name='counts_class')
n_categories = df_class.shape[0]
colors_class = [plt.cm.set3(i/float(n_categories)) for i in range(n_categories)]

# by cylinders data
df_cyl = df_raw.groupby('cyl').size().reset_index(name='counts_cyl')
n_categories = df_cyl.shape[0]
colors_cyl = [plt.cm.spectral(i/float(n_categories)) for i in range(n_categories)]

# by make data
df_make = df_raw.groupby('manufacturer').size().reset_index(name='counts_make')
n_categories = df_make.shape[0]
colors_make = [plt.cm.tab20b(i/float(n_categories)) for i in range(n_categories)]


# draw plot and decorate
fig = plt.figure(
    figureclass=waffle,
    plots={
        '311': {
            'values': df_class['counts_class'],
            'labels': ["{1}".format(n[0], n[1]) for n in df_class[['class', 'counts_class']].itertuples()],
            'legend': {'loc': 'upper left', 'bbox_to_anchor': (1.05, 1), 'fontsize': 12, 'title':'class'},
            'title': {'label': '# vehicles by class', 'loc': 'center', 'fontsize':18},
            'colors': colors_class
        },
        '312': {
            'values': df_cyl['counts_cyl'],
            'labels': ["{1}".format(n[0], n[1]) for n in df_cyl[['cyl', 'counts_cyl']].itertuples()],
            'legend': {'loc': 'upper left', 'bbox_to_anchor': (1.05, 1), 'fontsize': 12, 'title':'cyl'},
            'title': {'label': '# vehicles by cyl', 'loc': 'center', 'fontsize':18},
            'colors': colors_cyl
        },
        '313': {
            'values': df_make['counts_make'],
            'labels': ["{1}".format(n[0], n[1]) for n in df_make[['manufacturer', 'counts_make']].itertuples()],
            'legend': {'loc': 'upper left', 'bbox_to_anchor': (1.05, 1), 'fontsize': 12, 'title':'manufacturer'},
            'title': {'label': '# vehicles by make', 'loc': 'center', 'fontsize':18},
            'colors': colors_make
        }
    },
    rows=9,
    figsize=(16, 14)
)

 

2 饼图

饼图是显示组组成的经典方法。但是，如今一般不建议使用它，因为馅饼部分的面积有时可能会引起误解。因此，如果要使用饼图，强烈建议明确写下饼图各部分的百分比或数字。

# import
df_raw = pd.read_csv("data/mpg_ggplot2.csv")

# prepare data
df = df_raw.groupby('class').size()

# make the plot with pandas
df.plot(kind='pie', subplots=true, figsize=(8, 8), dpi= 80)
plt.title("pie chart of vehicle class - bad")
plt.ylabel("")
plt.show()

 

# import
df_raw = pd.read_csv("data/mpg_ggplot2.csv")

# prepare data
df = df_raw.groupby('class').size().reset_index(name='counts')

# draw plot
fig, ax = plt.subplots(figsize=(12, 7), subplot_kw=dict(aspect="equal"), dpi= 80)

data = df['counts']
categories = df['class']
explode = [0,0,0,0,0,0.1,0]

def func(pct, allvals):
    absolute = int(pct/100.*np.sum(allvals))
    return "{:.1f}% ({:d} )".format(pct, absolute)

wedges, texts, autotexts = ax.pie(data, 
                                  autopct=lambda pct: func(pct, data),
                                  textprops=dict(color="w"), 
                                  colors=plt.cm.dark2.colors,
                                 startangle=140,
                                 explode=explode)

# decoration
ax.legend(wedges, categories, title="vehicle class", loc="center left", bbox_to_anchor=(1, 0, 0.5, 1))
plt.setp(autotexts, size=10, weight=700)
ax.set_title("class of vehicles: pie chart")
plt.show()

 

3 树状图

树形图类似于饼形图，并且可以更好地完成工作，而不会误导每个组的贡献。

 

 

# pip install squarify
import squarify 

# import data
df_raw = pd.read_csv("data/mpg_ggplot2.csv")

# prepare data
df = df_raw.groupby('class').size().reset_index(name='counts')
labels = df.apply(lambda x: str(x[0]) + "\n (" + str(x[1]) + ")", axis=1)
sizes = df['counts'].values.tolist()
colors = [plt.cm.spectral(i/float(len(labels))) for i in range(len(labels))]

# draw plot
plt.figure(figsize=(12,8), dpi= 80)
squarify.plot(sizes=sizes, label=labels, color=colors, alpha=.8)

# decorate
plt.title('treemap of vechile class')
plt.axis('off')
plt.show()

 

4 条形图

条形图是一种基于计数或任何给定指标可视化项目的经典方法。在下面的图表中，我为每个项目使用了不同的颜色，但是您通常可能希望为所有项目选择一种颜色，除非您按组对它们进行着色。颜色名称存储在all_colors下面的代码中。您可以通过在中设置color参数来更改条形的颜色。

import random

# import data
df_raw = pd.read_csv("data/mpg_ggplot2.csv")

# prepare data
df = df_raw.groupby('manufacturer').size().reset_index(name='counts')
n = df['manufacturer'].unique().__len__()+1
all_colors = list(plt.cm.colors.cnames.keys())
random.seed(100)
c = random.choices(all_colors, k=n)

# plot bars
plt.figure(figsize=(16,10), dpi= 80)
plt.bar(df['manufacturer'], df['counts'], color=c, width=.5)
for i, val in enumerate(df['counts'].values):
    plt.text(i, val, float(val), horizontalalignment='center', verticalalignment='bottom', fontdict={'fontweight':500, 'size':12})

# decoration
plt.gca().set_xticklabels(df['manufacturer'], rotation=60, horizontalalignment= 'right')
plt.title("number of vehicles by manaufacturers", fontsize=22)
plt.ylabel('# vehicles')
plt.ylim(0, 45)
plt.show()

 

不管你是零基础还是有基础都可以获取到自己相对应的学习礼包！包括python软件工具和2020最新入门到实战教程。加群695185429即可免费获取。