Visualize_ch1

Python可视化的基础知识
作分析的数据文件和Jupyter文档都在这里：https://github.com/Clairewr/DA_ML_DL/tree/master/Visualize

Part I

import matplotlib.pyplot as plt
import pandas as pd
import warnings
warnings.filterwarnings('ignore')
data=pd.read_csv('percent-bachelors-degrees-women-usa.csv')
data.head()
data.count()

 

 

import matplotlib.pyplot as plt
plt.plot(year, physical_sciences, color='blue')
plt.plot(year,computer_science,color='red')
plt.show()

 

In calling plt.axes([xlo, ylo, width, height])

#Note that these coordinates can be passed to plt.axes() in the form of a list or a tuple.

# Create plot axes for the first line plot
plt.axes([0.05,0.05,0.425,0.9])   #注意传入的是个 List 或是 tuple

# Plot in blue the % of degrees awarded to women in the Physical Sciences
plt.plot(year, physical_sciences, color='blue')

# Create plot axes for the second line plot
plt.axes([0.525,0.05,0.425,0.9])

# Plot in red the % of degrees awarded to women in Computer Science
plt.plot(year, computer_science, color='red')

# Display the plot
plt.show()

Using subplot() 

The command plt.axes() requires a lot of effort to use well because the coordinates of the axes need to be set manually. A better alternative is to use plt.subplot() to determine the layout automatically.

#1x2 一行两列。 在使用plot前都需要先active对应的 subplot。

# Create a figure with 1x2 subplot and make the left subplot active
plt.subplot(1,2,1)

# Plot in blue the % of degrees awarded to women in the Physical Sciences
plt.plot(year, physical_sciences, color='blue')
plt.title('Physical Sciences')

# Make the right subplot active in the current 1x2 subplot grid

plt.subplot(1,2,2)
# Plot in red the % of degrees awarded to women in Computer Science
plt.plot(year, computer_science, color='red')
plt.title('Computer Science')

# Use plt.tight_layout() to improve the spacing between subplots
plt.tight_layout()
plt.show()

绘制一个2x2的 subplot，第三个位置参数按从左到右，从上到下分别为1,2,3,4

# Create a figure with 2x2 subplot layout and make the top left subplot active
plt.subplot(2,2,1)
plt.plot(year, physical_sciences, color='blue')
plt.title('Physical Sciences')

# Make the top right subplot active in the current 2x2 subplot grid 
plt.subplot(2,2,2)
plt.plot(year, computer_science, color='red')
plt.title('Computer Science')

# Make the bottom left subplot active in the current 2x2 subplot grid
plt.subplot(2,2,3)
plt.plot(year, health, color='green')
plt.title('Health Professions')

# Make the bottom right subplot active in the current 2x2 subplot grid
plt.subplot(2,2,4)
plt.plot(year, education, color='yellow')
plt.title('Education')

# Improve the spacing between subplots and display them
plt.tight_layout()
plt.show()

---

 

xlim, ylim用于截取部分区间，也即使focus on 局部数据 

# Plot the % of degrees awarded to women in Computer Science and the Physical Sciences
plt.plot(year,computer_science, color='red') 
plt.plot(year, physical_sciences, color='blue')

# Add the axis labels
plt.xlabel('Year')
plt.ylabel('Degrees awarded to women (%)')

# Set the x-axis range
plt.xlim(1990,2010)#  中间用逗号隔开

# Set the y-axis range
plt.ylim(0,50) # 这里的50就是： 50%

# Add a title and display the plot
plt.title('Degrees awarded to women (1990-2010)\nComputer Science (red)\nPhysical Sciences (blue)')
plt.show()

# Save the image as 'xlim_and_ylim.png'
plt.savefig('xlim_and_ylim.png')

 

与xlim, ylim同样的实现方法是用 plt.axis，传入list或tuple，注意区分axis(轴线)和axes(坐标轴), 我的理解是axis包含于axes

# Plot in blue the % of degrees awarded to women in Computer Science
plt.plot(year,computer_science, color='blue')

# Plot in red the % of degrees awarded to women in the Physical Sciences
plt.plot(year, physical_sciences,color='red')

# Set the x-axis and y-axis limits
plt.axis([1990,2010,0,50])

# Show the figure
plt.show()

# Save the figure as 'axis_limits.png'
plt.savefig('axis_limits.png')

plt.legend(loc='lower center')注意loc参数

# Specify the label 'Computer Science'
plt.plot(year, computer_science, color='red', label='Computer Science') 

# Specify the label 'Physical Sciences' 
plt.plot(year, physical_sciences, color='blue', label='Physical Sciences')

# Add a legend at the lower center
plt.legend(loc='lower center')

# Add axis labels and title
plt.xlabel('Year')
plt.ylabel('Enrollment (%)')
plt.title('Undergraduate enrollment of women')
plt.show()

 

# Plot with legend as before
plt.plot(year, computer_science, color='red', label='Computer Science') 
plt.plot(year, physical_sciences, color='blue', label='Physical Sciences')
plt.legend(loc='lower right')

# Compute the maximum enrollment of women in Computer Science: cs_max
cs_max = computer_science.max()

# Calculate the year in which there was maximum enrollment of women in Computer Science: yr_max
yr_max = year[computer_science.argmax()]#这里比较奇怪的是用x坐标的argmax()函数的返回值，作为year的index

# Add a black arrow annotation
plt.annotate('Maximum', xy=(yr_max, cs_max), xytext=(yr_max+5, cs_max+5), arrowprops=dict(facecolor='black'))#annotate的第一个参数是注释Label

# Add axis labels and title
plt.xlabel('Year')
plt.ylabel('Enrollment (%)')
plt.title('Undergraduate enrollment of women')
plt.show()

使用style:

# Import matplotlib.pyplot
import matplotlib.pyplot as plt

# Set the style to 'ggplot'
plt.style.use('ggplot')

# Create a figure with 2x2 subplot layout
plt.subplot(2, 2, 1) 

# Plot the enrollment % of women in the Physical Sciences
plt.plot(year, physical_sciences, color='blue')
plt.title('Physical Sciences')

# Plot the enrollment % of women in Computer Science
plt.subplot(2, 2, 2)
plt.plot(year, computer_science, color='red')
plt.title('Computer Science')

# Add annotation
cs_max = computer_science.max()
yr_max = year[computer_science.argmax()]
plt.annotate('Maximum', xy=(yr_max, cs_max), xytext=(yr_max-1, cs_max-10), arrowprops=dict(facecolor='black'))

# Plot the enrollmment % of women in Health professions
plt.subplot(2, 2, 3)
plt.plot(year, health, color='green')
plt.title('Health Professions')

# Plot the enrollment % of women in Education
plt.subplot(2, 2, 4)
plt.plot(year, education, color='yellow')
plt.title('Education')

# Improve spacing between subplots and display them
plt.tight_layout()
plt.show()