今天分享给大家25个Matplotlib图的汇编,在数据分析和可视化中最有用。
# !pip install brewer2mpl import numpy as np import pandas as pd import matplotlib as mpl import matplotlib.pyplot as plt import seaborn as sns import warnings; warnings.filterwarnings(action='once') large = 22; med = 16; small = 12 params = {'axes.titlesize': large, 'legend.fontsize': med, 'figure.figsize': (16, 10), 'axes.labelsize': med, 'axes.titlesize': med, 'xtick.labelsize': med, 'ytick.labelsize': med, 'figure.titlesize': large} plt.rcParams.update(params) plt.style.use('seaborn-whitegrid') sns.set_style("white") %matplotlib inline # Version print(mpl.__version__) #> 3.0.0 print(sns.__version__) #> 0.9.0
文末惊喜不断~
1. 散点图
Scatteplot是用于研究两个变量之间关系的经典和基本图。如果数据中有多个组,则可能需要以不同颜色可视化每个组。在Matplotlib,你可以方便地使用。
# Import dataset midwest = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/midwest_filter.csv") # Prepare Data # Create as many colors as there are unique midwest['category'] categories = np.unique(midwest['category']) colors = [plt.cm.tab10(i/float(len(categories)-1)) for i in range(len(categories))] # Draw Plot for Each Category plt.figure(figsize=(16, 10), dpi= 80, facecolor='w', edgecolor='k') for i, category in enumerate(categories): plt.scatter('area', 'poptotal', data=midwest.loc[midwest.category==category, :], s=20, c=colors[i], label=str(category)) # Decorations plt.gca().set(xlim=(0.0, 0.1), ylim=(0, 90000), xlabel='Area', ylabel='Population') plt.xticks(fontsize=12); plt.yticks(fontsize=12) plt.title("Scatterplot of Midwest Area vs Population", fontsize=22) plt.legend(fontsize=12) plt.show()
2. 带边界的气泡图
有时,您希望在边界内显示一组点以强调其重要性。在此示例中,您将从应该被环绕的数据帧中获取记录,并将其传递给下面的代码中描述的记录。encircle()
from matplotlib import patches from scipy.spatial import ConvexHull import warnings; warnings.simplefilter('ignore') sns.set_style("white") # Step 1: Prepare Data midwest = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/midwest_filter.csv") # As many colors as there are unique midwest['category'] categories = np.unique(midwest['category']) colors = [plt.cm.tab10(i/float(len(categories)-1)) for i in range(len(categories))] # Step 2: Draw Scatterplot with unique color for each category fig = plt.figure(figsize=(16, 10), dpi= 80, facecolor='w', edgecolor='k')