# 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))
plt.xticks(fontsize=12); plt.yticks(fontsize=12) plt.title("Scatterplot of Midwest Area vs Population", fontsize=22) plt.legend(fontsize=12) plt.show()
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')
for i, category in enumerate(categories): plt.scatter('area', 'poptotal', data=midwest.loc[midwest.category==category, :], s='dot_size', c=colors[i], label=str(category), edgecolors='black', linewidths=.5)
# Step 3: Encircling # https://stackoverflow.com/questions/44575681/how-do-i-encircle-different-data-sets-in-scatter-plot def encircle(x,y, ax=None, **kw): if not ax: ax=plt.gca() p = np.c_[x,y] hull = ConvexHull(p) poly = plt.Polygon(p[hull.vertices,:], **kw) ax.add_patch(poly)
# Select data to be encircled midwest_encircle_data = midwest.loc[midwest.state=='IN', :]
# Import Data df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/mpg_ggplot2.csv") df_select = df.loc[df.cyl.isin([4,8]), :]
# Each line in its own column sns.set_style("white") gridobj = sns.lmplot(x="displ", y="hwy", data=df_select, height=7, robust=True, palette='Set1', col="cyl", scatter_kws=dict(s=60, linewidths=.7, edgecolors='black'))
# Scatterplot on main ax ax_main.scatter('displ', 'hwy', s=df.cty*5, c=df.manufacturer.astype('category').cat.codes, alpha=.9, data=df, cmap="Set1", edgecolors='black', linewidths=.5)
# Add a graph in each part sns.boxplot(df.hwy, ax=ax_right, orient="v") sns.boxplot(df.displ, ax=ax_bottom, orient="h")
# Decorations ------------------ # Remove x axis name for the boxplot ax_bottom.set(xlabel='') ax_right.set(ylabel='')
# Main Title, Xlabel and YLabel ax_main.set(title='Scatterplot with Histograms displ vs hwy', xlabel='displ', ylabel='hwy')
# Set font size of different components ax_main.title.set_fontsize(20) for item in ([ax_main.xaxis.label, ax_main.yaxis.label] + ax_main.get_xticklabels() + ax_main.get_yticklabels()): item.set_fontsize(14)
# Decorations plt.gca().set(ylabel='$Model$', xlabel='$Mileage$') plt.yticks(df.index, df.cars, fontsize=12) plt.title('Diverging Bars of Car Mileage', fontdict={'size':20}) plt.grid(linestyle='--', alpha=0.5) plt.show()
11. 发散型文本
分散的文本类似于发散条，如果你想以一种漂亮和可呈现的方式显示图表中每个项目的价值，它更喜欢。
# Prepare Data df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mtcars.csv") x = df.loc[:, ['mpg']] df['mpg_z'] = (x - x.mean())/x.std() df['colors'] = ['red'if x else 'green'for x in df['mpg_z']] df.sort_values('mpg_z', inplace=True) df.reset_index(inplace=True)
# Draw plot plt.figure(figsize=(14,14), dpi= 80) plt.hlines(y=df.index, xmin=0, xmax=df.mpg_z) for x, y, tex in zip(df.mpg_z, df.index, df.mpg_z): t = plt.text(x, y, round(tex, 2), horizontalalignment='right'if x else 'left', verticalalignment='center', fontdict={'color':'red'if x else 'green', 'size':14})
# Decorations plt.yticks(df.index, df.cars, fontsize=12) plt.title('Diverging Text Bars of Car Mileage', fontdict={'size':20}) plt.grid(linestyle='--', alpha=0.5) plt.xlim(-2.5, 2.5) plt.show()
12. 发散型包点图
发散点图也类似于发散条。然而，与发散条相比，条的不存在减少了组之间的对比度和差异。
# Prepare Data df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mtcars.csv") x = df.loc[:, ['mpg']] df['mpg_z'] = (x - x.mean())/x.std() df['colors'] = ['red'if x else 'darkgreen'for x in df['mpg_z']] df.sort_values('mpg_z', inplace=True) df.reset_index(inplace=True)
# Draw plot plt.figure(figsize=(14,16), dpi= 80) plt.scatter(df.mpg_z, df.index, s=450, alpha=.6, color=df.colors) for x, y, tex in zip(df.mpg_z, df.index, df.mpg_z): t = plt.text(x, y, round(tex, 1), horizontalalignment='center', verticalalignment='center', fontdict={'color':'white'})
# Title, Label, Ticks and Ylim ax.set_title('Dot Plot for Highway Mileage', fontdict={'size':22}) ax.set_xlabel('Miles Per Gallon') ax.set_yticks(df.index) ax.set_yticklabels(df.manufacturer.str.title(), fontdict={'horizontalalignment': 'right'}) ax.set_xlim(10, 27) plt.show()
18. 坡度图
斜率图最适合比较给定人/项目的“之前”和“之后”位置。
import matplotlib.lines as mlines # Import Data df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/gdppercap.csv")
left_label = [str(c) + ', '+ str(round(y)) for c, y in zip(df.continent, df['1952'])] right_label = [str(c) + ', '+ str(round(y)) for c, y in zip(df.continent, df['1957'
])] klass = ['red'if (y1-y2) else 'green'for y1, y2 in zip(df['1952'], df['1957'])]
# draw line # https://stackoverflow.com/questions/36470343/how-to-draw-a-line-with-matplotlib/36479941 def newline(p1, p2, color='black'): ax = plt.gca() l = mlines.Line2D([p1[0],p2[0]], [p1[1],p2[1]], color='red'if p1[1]-p2[1] > 0 else'green', marker='o', markersize=6) ax.add_line(l) return l
# Decoration ax.set_title("Slopechart: Comparing GDP Per Capita between 1952 vs 1957", fontdict={'size':22}) ax.set(xlim=(0,4), ylim=(0,14000), ylabel='Mean GDP Per Capita') ax.set_xticks([1,3]) ax.set_xticklabels(["1952", "1957"]) plt.yticks(np.arange(500, 13000, 2000), fontsize=12)
# Import Data df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv")
# Prepare data x_var = 'displ' groupby_var = 'class' df_agg = df.loc[:, [x_var, groupby_var]].groupby(groupby_var) vals = [df[x_var].values.tolist() for i, df in df_agg]
# Draw plt.figure(figsize=(16,9), dpi= 80) colors = [plt.cm.Spectral(i/float(len(vals)-1)) for i in range(len(vals))] n, bins, patches = plt.hist(vals, 30, stacked=True, density=False, color=colors[:len(vals)])
# Decoration plt.legend({group:col for group, col in zip(np.unique(df[groupby_var]).tolist(), colors[:len(vals)])}) plt.title(f"Stacked Histogram of ${x_var}$ colored by ${groupby_var}$", fontsize=22) plt.xlabel(x_var) plt.ylabel("Frequency") plt.ylim(0, 25) plt.xticks(ticks=bins[::3], labels=[round(b,1) for b in bins[::3]]) plt.show()
# Mean and Median city mileage by make df = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.mean()) df.sort_values('cty', ascending=False, inplace=True) df.reset_index(inplace=True) df_median = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.median())
