↑
1. 前言
2. pandas
import pandas as pd
df = pd.read_csv('temporal.csv')
df.head(10) #View first 10 data rows
df.describe()
df.info()
pd.set_option('display.max_rows',500)
pd.set_option('display.max_columns',500)
pd.set_option('display.width',1000)
format_dict = {'data science':'${0:,.2f}', 'Mes':'{:%m-%Y}', 'machine learning':'{:.2%}'}
#We make sure that the Month column has datetime format
df['Mes'] = pd.to_datetime(df['Mes'])
#We apply the style to the visualization
df.head().style.format(format_dict)
format_dict = {'Mes':'{:%m-%Y}'} #Simplified format dictionary with values that do make sense for our data
df.head().style.format(format_dict).highlight_max(color='darkgreen').highlight_min(color='#ff0000')
df.head(10).style.format(format_dict).background_gradient(subset=['data science', 'machine learning'], cmap='BuGn')
df.head().style.format(format_dict).bar(color='red', subset=['data science', 'deep learning'])
df.head(10).style.format(format_dict).background_gradient(subset = ['data science','machine learning'],cmap ='BuGn')。highlight_max(color ='yellow')
from pandas_profiling import ProfileReport
prof = ProfileReport(df)
prof.to_file(output_file='report.html')
3. matplotlib
import matplotlib.pyplot as plt
plt.plot(df['Mes'], df['data science'], label='data science')
# The parameter label is to indicate the legend. This doesn't mean that it will be shown, we'll have to use another command that I'll explain later.
plt.plot(df ['Mes'],df ['data science'],label ='data science')
plt.plot(df ['Mes'],df ['machine learning'],label ='machine learning ')
plt.plot(df ['Mes'],df ['deep learning'],label ='deep learning')
plt.plot(df['Mes'], df['data science'], label='data science')
plt.plot(df['Mes'], df['machine learning'], label='machine learning')
plt.plot(df['Mes'], df['deep learning'], label='deep learning')
plt.xlabel('Date')
plt.ylabel('Popularity')
plt.title('Popularity of AI terms by date')
plt.grid(True)
plt.legend()
fig, axes = plt.subplots(2,2)
axes[0, 0].hist(df['data science'])
axes[0, 1].scatter(df['Mes'], df['data science'])
axes[1, 0].plot(df['Mes'], df['machine learning'])
axes[1, 1].plot(df['Mes'], df['deep learning'])
plt.plot(df ['Mes'],df ['data science'],'r-')
plt.plot(df ['Mes'],df ['data science'] * 2,'bs')
plt .plot(df ['Mes'],df ['data science'] * 3,'g ^')
plt.scatter(df['data science'], df['machine learning'])
plt.bar(df ['Mes'],df ['machine learning'],width = 20)
plt.hist(df ['deep learning'],bins = 15)
plt.plot(df['Mes'], df['data science'], label='data science')
plt.plot(df['Mes'], df['machine learning'], label='machine learning')
plt.plot(df['Mes'], df['deep learning'], label='deep learning')
plt.xlabel('Date')
plt.ylabel('Popularity')
plt.title('Popularity of AI terms by date')
plt.grid(True)
plt.text(x='2010-01-01', y=80, s=r'$\lambda=1, r^2=0.8$') #Coordinates use the same units as the graph
plt.annotate('Notice something?', xy=('2014-01-01', 30), xytext=('2006-01-01', 50), arrowprops={'facecolor':'red', 'shrink':0.05}
4. seaborn
import seaborn as sns
sns.set()
sns.scatterplot(df['Mes'], df['data science'])
sns.relplot(x='Mes', y='deep learning', hue='data science', size='machine learning', col='categorical', data=df)
sns.heatmap(df.corr(),annot = True,fmt ='。2f')
sns.pairplot(df)
sns.pairplot(df,hue ='categorical')
sns.jointplot(x='data science', y='machine learning', data=df)
sns.catplot(x='categorical', y='data science', kind='violin', data=df)
fig, axes = plt.subplots(1, 2, sharey=True, figsize=(8, 4))
sns.scatterplot(x="Mes", y="deep learning", hue="categorical", data=df, ax=axes[0])
axes[0].set_title('Deep Learning')
sns.scatterplot(x="Mes", y="machine learning", hue="categorical", data=df, ax=axes[1])
axes[1].set_title('Machine Learning')
5. Bokeh
from bokeh.plotting import figure, output_file, save
output_file('data_science_popularity.html')
p = figure(title='data science', x_axis_label='Mes', y_axis_label='data science')
p.line(df['Mes'], df['data science'], legend='popularity', line_width=2)
save(p)
output_file('multiple_graphs.html')
s1 = figure(width=250, plot_height=250, title='data science')
s1.circle(df['Mes'], df['data science'], size=10, color='navy', alpha=0.5)
s2 = figure(width=250, height=250, x_range=s1.x_range, y_range=s1.y_range, title='machine learning') #share both axis range
s2.triangle(df['Mes'], df['machine learning'], size=10, color='red', alpha=0.5)
s3 = figure(width=250, height=250, x_range=s1.x_range, title='deep learning') #share only one axis range
s3.square(df['Mes'], df['deep learning'], size=5, color='green', alpha=0.5)
p = gridplot([[s1, s2, s3]])
save(p)
6. altair
7. folium
import folium
m1 = folium.Map(location=[41.38, 2.17], tiles='openstreetmap', zoom_start=18)
m1.save('map1.html')
m2 = folium.Map(location=[41.38, 2.17], tiles='openstreetmap', zoom_start=16)
folium.Marker([41.38, 2.176], popup='<i>You can use whatever HTML code you want</i>', tooltip='click here').add_to(m2)
folium.Marker([41.38, 2.174], popup='<b>You can use whatever HTML code you want</b>', tooltip='dont click here').add_to(m2)
m2.save('map2.html')
from geopandas.tools import geocode
df2 = pd.read_csv('mapa.csv')
df2.dropna(axis=0, inplace=True)
df2['geometry'] = geocode(df2['País'], provider='nominatim')['geometry'] #It may take a while because it downloads a lot of data.
df2['Latitude'] = df2['geometry'].apply(lambda l: l.y)
df2['Longitude'] = df2['geometry'].apply(lambda l: l.x)
m3 = folium.Map(location=[39.326234,-4.838065], tiles='openstreetmap', zoom_start=3)
def color_producer(val):
if val <= 50:
return 'red'
else:
return 'green'
for i in range(0,len(df2)):
folium.Circle(location=[df2.iloc[i]['Latitud'], df2.iloc[i]['Longitud']], radius=5000*df2.iloc[i]['data science'], color=color_producer(df2.iloc[i]['data science'])).add_to(m3)
m3.save('map3.html')
如果你觉得文章还不错,请大家 点赞、分享、留言 下,因为这将是我持续输出更多优质文章的最强动力!
零基础学 Python,来这里
只需7天时间,跨进Python编程大门,已有3800+加入
【基础】0基础入门python,24小时有人快速解答问题;
【提高】40多个项目实战,老手可以从真实场景中学习python;
【直播】不定期直播项目案例讲解,手把手教你如何分析项目;
【分享】优质python学习资料分享,让你在最短时间获得有价值的学习资源;圈友优质资料或学习分享,会不时给予赞赏支持,希望每个优质圈友既能赚回加入费用,也能快速成长,并享受分享与帮助他人的乐趣。
【人脉】收获一群志同道合的朋友,并且都是python从业者
【价格】本着布道思想,只需 69元 加入一个能保证学习效果的良心圈子。【赠予】后续圈主将开发python,0基础入门在线课程,免费送给圈友们,供巩固和系统化复习
(三重福利)最近入圈送大礼包:
1、2.7G、308份最新数据分析报告
2、40G 人工智能算法 视频课
3、Python爬虫课,共14课
更多精彩
在公众号后台对话框输入以下关键词
查看更多优质内容!
PM2.5 | 世界杯 | 惊喜 | 附书代码
觉得不错,请把这篇文章分享给你的朋友
转载 / 投稿请联系:data_circle_yoni
● 手把手 | 爬取京东评论,且修改网址直接可复用哦(送代码)