数据分析及可视化 散点图的绘制

Python数据可视化之散点图的绘制

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
df = pd.read_csv('C:/Users/asus/Desktop/jintiguan/transcount.csv')
df = df.groupby('year').aggregate(np.mean)   # 提取数据
gpu = pd.read_csv('C:/Users/asus/Desktop/jintiguan/gpu_transcount.csv')
gpu = gpu.groupby('year').aggregate(np.mean) # 提取数据
df = pd.merge(df,gpu,how = 'outer',left_index = True,right_index = True)
df = df.replace(np.nan,0)
years = df.index.values

counts = df['trans_count'].values
gpu_counts = df['gpu_trans_count'].values
cnt_log = np.log(counts)
plt.scatter(years,cnt_log,c = 200 * years,s = 20 + 200 * gpu_counts / gpu_counts.max(),alpha = 0.5)
plt.show()

# 绘制箭头
gpu_start = gpu.index.values.min()
y_ann = np.log(df.at[gpu_start,'trans_count'])
ann_str = "First GPU\n %d"%gpu_start   #设置箭头的标签
plt.annotate(ann_str,xy = (gpu_start,y_ann),arrowprops = dict(arrowstyle = "->"),xytext = (-30,+70),textcoords = 'offset points')  #在指定位置绘制箭头

# 绘制散点图
cnt_log = np.log(counts)  # 求y轴均值的对数
plt.scatter(years,cnt_log,c = 200 * years,s = 20 + 200 * gpu_counts / gpu_counts.max(),alpha = 0.5,label = "Scatter")  #绘制散点图，在绘画的同时进行纵坐标的均值的对数计算
plt.legend(loc = "upper left")  #设置图例的位置，upper left：左上
plt.grid()  # 绘制背景辅助线（灰线）
plt.xlabel("Year")    # 设置x轴标签
plt.ylabel("Log Transistor Counts",fontsize = 16)   # 设置y轴标签
plt.title("Moore's Law & Transistor Counts")   # 设置大标题
plt.show()

数据文件网盘自取：https://pan.baidu.com/s/1cmOI_IVPWOiwiLXS-993Xg
提取码：fiw2