plt.scatter散点图

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

df = pd.read_csv("transcount.csv")
df = df.groupby("Date of introduction").aggregate(np.mean)

gpu = pd.read_csv("gpu_transcount.csv")
gpu = gpu.groupby("Date of introduction").aggregate(np.mean)

df = pd.merge(df, gpu, how="outer", left_index=True, right_index=True)
df = df.replace(np.nan, 0)

print(df)
years = df.index.values
counts = df['Transistor count_x'].values
gpu_counts = df['Transistor count_y'].values

poly = np.polyfit(years, np.log(counts), deg = 1)
plt.plot(years, np.polyval(poly, years), label='Fit')

gpu_start = gpu.index.values.min()
y_ann = np.log(df.at[gpu_start, 'Transistor count_x'])
ann_str = "First GPU\n %d" %gpu_start
plt.annotate(ann_str, xy = (gpu_start, y_ann), arrowprops=dict(arrowstyle="->"), xytext=(-30, + 70), textcoords="offset points")

cnt_log= np.log(counts)
plt.scatter(years, cnt_log, c = 200 * years, s=20 + 200 * gpu_counts/gpu_counts.max(), alpha=0.5, label="Scatter Plot")
plt.legend(loc='upper left')
plt.grid()
plt.xlabel("Year")
plt.ylabel("Log Transistor Counts", fontsize=16)
plt.title("Moore's Law & Transistor Counts")
plt.show()