偶然看到网上国家统计数据，利用Python数据分析自己做了几种图表练习。主要采用Pandas来做数据统计，matplotlib来做图表可视化。
下面图表数据来源于网络。
热图
代码如下：
代码语言：python代码运行次数：0复制
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import itertools
from mpl_toolkits.axes_grid1.inset_locator import inset_axes
plt.rcParams['font.family']='sans-serif'
plt.rcParams['font.sans-serif']='SimHei'
df=pd.read_excel('d:/2018-2019年空气质量均值.xlsx')
df2=pd.read_excel('d:/2018-2019年空气质量均值.xlsx',1)
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
# sphinx_gallery_thumbnail_number = 2
colNames=["二氧化硫","氮氧化物","烟尘","排放总量"]
years=["2018","2019"]
regionTypes=["省辖市","市辖区"]
def heatmap(data, row_labels, col_labels, ax=None,
cbar_kw={}, cbarlabel="", **kwargs):
"""
Create a heatmap from a numpy array and two lists of labels.
Parameters
----------
data
A 2D numpy array of shape (N, M).
row_labels
A list or array of length N with the labels for the rows.
col_labels
A list or array of length M with the labels for the columns.
ax
A `matplotlib.axes.Axes` instance to which the heatmap is plotted. If
not provided, use current axes or create a new one. Optional.
cbar_kw
A dictionary with arguments to `matplotlib.Figure.colorbar`. Optional.
cbarlabel
The label for the colorbar. Optional.
**kwargs
All other arguments are forwarded to `imshow`.
"""
if not ax:
ax = plt.gca()
# Plot the heatmap
im = ax.imshow(data, **kwargs)
# Create colorbar
cbar = ax.figure.colorbar(im, ax=ax,orientation='vertical',**cbar_kw)
cbar.ax.set_ylabel(cbarlabel, rotation=-90, va="bottom")
# We want to show all ticks...
ax.set_xticks(np.arange(data.shape[1]))
ax.set_yticks(np.arange(data.shape[0]))
# ... and label them with the respective list entries.
ax.set_xticklabels(col_labels)
ax.set_yticklabels(row_labels)
# Let the horizontal axes labeling appear on top.
ax.tick_params(top=True, bottom=False,
labeltop=True, labelbottom=False)
# Rotate the tick labels and set their alignment.
plt.setp(ax.get_xticklabels(), rotation=-30, ha="right",
rotation_mode="anchor")
# Turn spines off and create white grid.
for edge, spine in ax.spines.items():
spine.set_visible(False)
ax.set_xticks(np.arange(data.shape[1] 1)-.5, minor=True)
ax.set_yticks(np.arange(data.shape[0] 1)-.5, minor=True)
ax.grid(which="minor", color="w", linestyle='-', linewidth=3)
ax.tick_params(which="minor", bottom=False, left=False)
return im, cbar
def annotate_heatmap(im, data=None, valfmt="{x:.2f}",
textcolors=("black", "white"),
threshold=None, **textkw):
"""
A function to annotate a heatmap.
Parameters
----------
im
The AxesImage to be labeled.
data
Data used to annotate. If None, the image's data is used. Optional.
valfmt
The format of the annotations inside the heatmap. This should either
use the string format method, e.g. "$ {x:.2f}", or be a
`matplotlib.ticker.Formatter`. Optional.
textcolors
A pair of colors. The first is used for values below a threshold,
the second for those above. Optional.
threshold
Value in data units according to which the colors from textcolors are
applied. If None (the default) uses the middle of the colormap as
separation. Optional.
**kwargs
All other arguments are forwarded to each call to `text` used to create
the text labels.
"""
if not isinstance(data, (list, np.ndarray)):
data = im.get_array()
# Normalize the threshold to the images color range.
if threshold is not None:
threshold = im.norm(threshold)
else:
threshold = im.norm(data.max())/2.
# Set default alignment to center, but allow it to be
# overwritten by textkw.
kw = dict(horizontalalignment="center",
verticalalignment="center")
kw.update(textkw)
# Get the formatter in case a string is supplied
if isinstance(valfmt, str):
valfmt = matplotlib.ticker.StrMethodFormatter(valfmt)
# Loop over the data and create a `Text` for each "pixel".
# Change the text's color depending on the data.
texts = []
for i in range(data.shape[0]):
for j in range(data.shape[1]):
kw.update(color=textcolors[int(im.norm(data[i, j]) > threshold)])
text = im.axes.text(j, i, valfmt(data[i, j], None), **kw)
texts.append(text)
return texts
def getPlot(colName,year,regionType):
df22=df2
if regionType=="市辖区":
df22=df2[df2['城市名']!='济源市']
g=df22.groupby(['月份','城市名'],sort=False).first()
months = g.index.unique(level='月份').map(lambda x:str(x) '月')
citys = g.index.unique(level='城市名')
colStr='%s年%s_%s'%(year,colName,regionType)
values = g[colStr].values.reshape((citys.size,months.size)).transpose()
fig, ax = plt.subplots(figsize=(12,10))
im, cbar = heatmap(values, months, citys, ax=ax,
cmap='Wistia', cbarlabel="%s[吨/月]"%colName)
texts = annotate_heatmap(im, valfmt="{x:.0f}t")
title='%s年各地市%s月度排放量(%s)'%(year,colName,regionType)
plt.title(title)
#fig.tight_layout()
plt.savefig(title '.png')
for colName,year,regionType in itertools.product(colNames,years,regionTypes):
print(colName,year,regionType)
getPlot(colName,year,regionType)
