数据分析最有用的25个 Matplotlib图（二）-CDA数据分析师官网

import numpy as np import pandas as pd # Prepare Data df = pd.read_csv("https://github.com/selva86/datasets/raw/master/economics.csv", parse_dates=['date']).head(100) x = np.arange(df.shape[0]) y_returns = (df.psavert.diff().fillna(0)/df.psavert.shift(1)).fillna(0) * 100 # Plot plt.figure(figsize=(16,10), dpi= 80) plt.fill_between(x[1:], y_returns[1:], 0, where=y_returns[1:] >= 0, facecolor='green', interpolate=True, alpha=0.7) plt.fill_between(x[1:], y_returns[1:], 0, where=y_returns[1:] <= 0, facecolor='red', interpolate=True, alpha=0.7) # Annotate plt.annotate('Peak 1975', xy=(94.0, 21.0), xytext=(88.0, 28), bbox=dict(boxstyle='square', fc='firebrick'), arrowprops=dict(facecolor='steelblue', shrink=0.05), fontsize=15, color='white') # Decorations xtickvals = [str(m)[:3].upper()+"-"+str(y) for y,m in zip(df.date.dt.year, df.date.dt.month_name())] plt.gca().set_xticks(x[::6]) plt.gca().set_xticklabels(xtickvals[::6], rotation=90, fontdict={'horizontalalignment': 'center', 'verticalalignment': 'center_baseline'}) plt.ylim(-35,35) plt.xlim(1,100) plt.title("Month Economics Return %", fontsize=22) plt.ylabel('Monthly returns %') plt.grid(alpha=0.5) plt.show()

# Prepare Data df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv") df = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.mean()) df.sort_values('cty', inplace=True) df.reset_index(inplace=True) # Draw plot import matplotlib.patches as patches fig, ax = plt.subplots(figsize=(16,10), facecolor='white', dpi= 80) ax.vlines(x=df.index, ymin=0, ymax=df.cty, color='firebrick', alpha=0.7, linewidth=20) # Annotate Text for i, cty in enumerate(df.cty): ax.text(i, cty+0.5, round(cty, 1), horizontalalignment='center') # Title, Label, Ticks and Ylim ax.set_title('Bar Chart for Highway Mileage', fontdict={'size':22}) ax.set(ylabel='Miles Per Gallon', ylim=(0, 30)) plt.xticks(df.index, df.manufacturer.str.upper(), rotation=60, horizontalalignment='right', fontsize=12) # Add patches to color the X axis labels p1 = patches.Rectangle((.57, -0.005), width=.33, height=.13, alpha=.1, facecolor='green', transform=fig.transFigure) p2 = patches.Rectangle((.124, -0.005), width=.446, height=.13, alpha=.1, facecolor='red', transform=fig.transFigure) fig.add_artist(p1) fig.add_artist(p2) plt.show()

# Prepare Data df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv") df = df_raw[['cty', 'manufacturer']].groupby('manufacturer').apply(lambda x: x.mean()) df.sort_values('cty', inplace=True) df.reset_index(inplace=True) # Draw plot fig, ax = plt.subplots(figsize=(16,10), dpi= 80) ax.vlines(x=df.index, ymin=0, ymax=df.cty, color='firebrick', alpha=0.7, linewidth=2) ax.scatter(x=df.index, y=df.cty, s=75, color='firebrick', alpha=0.7) # Title, Label, Ticks and Ylim ax.set_title('Lollipop Chart for Highway Mileage', fontdict={'size':22}) ax.set_ylabel('Miles Per Gallon') ax.set_xticks(df.index) ax.set_xticklabels(df.manufacturer.str.upper(), rotation=60, fontdict={'horizontalalignment': 'right', 'size':12}) ax.set_ylim(0, 30) # Annotate for row in df.itertuples(): ax.text(row.Index, row.cty+.5, s=round(row.cty, 2), horizontalalignment= 'center', verticalalignment='bottom', fontsize=14) plt.show()

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) < 0 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 fig, ax = plt.subplots(1,1,figsize=(14,14), dpi= 80) # Vertical Lines ax.vlines(x=1, ymin=500, ymax=13000, color='black', alpha=0.7, linewidth=1, linestyles='dotted') ax.vlines(x=3, ymin=500, ymax=13000, color='black', alpha=0.7, linewidth=1, linestyles='dotted') # Points ax.scatter(y=df['1952'], x=np.repeat(1, df.shape[0]), s=10, color='black', alpha=0.7) ax.scatter(y=df['1957'], x=np.repeat(3, df.shape[0]), s=10, color='black', alpha=0.7) # Line Segmentsand Annotation for p1, p2, c in zip(df['1952'], df['1957'], df['continent']): newline([1,p1], [3,p2]) ax.text(1-0.05, p1, c + ', ' + str(round(p1)), horizontalalignment='right', verticalalignment='center', fontdict={'size':14}) ax.text(3+0.05, p2, c + ', ' + str(round(p2)), horizontalalignment='left', verticalalignment='center', fontdict={'size':14}) # 'Before' and 'After' Annotations ax.text(1-0.05, 13000, 'BEFORE', horizontalalignment='right', verticalalignment='center', fontdict={'size':18, 'weight':700}) ax.text(3+0.05, 13000, 'AFTER', horizontalalignment='left', verticalalignment='center', fontdict={'size':18, 'weight':700}) # 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) # Lighten borders plt.gca().spines["top"].set_alpha(.0) plt.gca().spines["bottom"].set_alpha(.0) plt.gca().spines["right"].set_alpha(.0) plt.gca().spines["left"].set_alpha(.0) plt.show()

import matplotlib.lines as mlines # Import Data df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/health.csv") df.sort_values('pct_2014', inplace=True) df.reset_index(inplace=True) # Func to draw line segment def newline(p1, p2, color='black'): ax = plt.gca() l = mlines.Line2D([p1[0],p2[0]], [p1[1],p2[1]], color='skyblue') ax.add_line(l) return l # Figure and Axes fig, ax = plt.subplots(1,1,figsize=(14,14), facecolor='#f7f7f7', dpi= 80) # Vertical Lines ax.vlines(x=.05, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted') ax.vlines(x=.10, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted') ax.vlines(x=.15, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted') ax.vlines(x=.20, ymin=0, ymax=26, color='black', alpha=1, linewidth=1, linestyles='dotted') # Points ax.scatter(y=df['index'], x=df['pct_2013'], s=50, color='#0e668b', alpha=0.7) ax.scatter(y=df['index'], x=df['pct_2014'], s=50, color='#a3c4dc', alpha=0.7) # Line Segments for i, p1, p2 in zip(df['index'], df['pct_2013'], df['pct_2014']): newline([p1, i], [p2, i]) # Decoration ax.set_facecolor('#f7f7f7') ax.set_title("Dumbell Chart: Pct Change - 2013 vs 2014", fontdict={'size':22}) ax.set(xlim=(0,.25), ylim=(-1, 27), ylabel='Mean GDP Per Capita') ax.set_xticks([.05, .1, .15, .20]) ax.set_xticklabels(['5%', '15%', '20%', '25%']) ax.set_xticklabels(['5%', '15%', '20%', '25%']) plt.show()

# 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()

# Import Data df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv") # Prepare data x_var = 'manufacturer' 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, df[x_var].unique().__len__(), 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, 40) plt.xticks(ticks=bins, labels=np.unique(df[x_var]).tolist(), rotation=90, horizontalalignment='left') plt.show()

# Import Data df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv") # Draw Plot plt.figure(figsize=(16,10), dpi= 80) sns.kdeplot(df.loc[df['cyl'] == 4, "cty"], shade=True, color="g", label="Cyl=4", alpha=.7) sns.kdeplot(df.loc[df['cyl'] == 5, "cty"], shade=True, color="deeppink", label="Cyl=5", alpha=.7) sns.kdeplot(df.loc[df['cyl'] == 6, "cty"], shade=True, color="dodgerblue", label="Cyl=6", alpha=.7) sns.kdeplot(df.loc[df['cyl'] == 8, "cty"], shade=True, color="orange", label="Cyl=8", alpha=.7) # Decoration plt.title('Density Plot of City Mileage by n_Cylinders', fontsize=22) plt.legend()

# Import Data df = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv") # Draw Plot plt.figure(figsize=(13,10), dpi= 80) sns.distplot(df.loc[df['class'] == 'compact', "cty"], color="dodgerblue", label="Compact", hist_kws={'alpha':.7}, kde_kws={'linewidth':3}) sns.distplot(df.loc[df['class'] == 'suv', "cty"], color="orange", label="SUV", hist_kws={'alpha':.7}, kde_kws={'linewidth':3}) sns.distplot(df.loc[df['class'] == 'minivan', "cty"], color="g", label="minivan", hist_kws={'alpha':.7}, kde_kws={'linewidth':3}) plt.ylim(0, 0.35) # Decoration plt.title('Density Plot of City Mileage by Vehicle Type', fontsize=22) plt.legend() plt.show()

# !pip install joypy # Import Data mpg = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv") # Draw Plot plt.figure(figsize=(16,10), dpi= 80) fig, axes = joypy.joyplot(mpg, column=['hwy', 'cty'], by="class", ylim='own', figsize=(14,10)) # Decoration plt.title('Joy Plot of City and Highway Mileage by Class', fontsize=22) plt.show()

import matplotlib.patches as mpatches # Prepare Data df_raw = pd.read_csv("https://github.com/selva86/datasets/raw/master/mpg_ggplot2.csv") cyl_colors = {4:'tab:red', 5:'tab:green', 6:'tab:blue', 8:'tab:orange'} df_raw['cyl_color'] = df_raw.cyl.map(cyl_colors) # 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()) # Draw horizontal lines fig, ax = plt.subplots(figsize=(16,10), dpi= 80) ax.hlines(y=df.index, xmin=0, xmax=40, color='gray', alpha=0.5, linewidth=.5, linestyles='dashdot') # Draw the Dots for i, make in enumerate(df.manufacturer): df_make = df_raw.loc[df_raw.manufacturer==make, :] ax.scatter(y=np.repeat(i, df_make.shape[0]), x='cty', data=df_make, s=75, edgecolors='gray', c='w', alpha=0.5) ax.scatter(y=i, x='cty', data=df_median.loc[df_median.index==make, :], s=75, c='firebrick') # Annotate ax.text(33, 13, "$red ; dots ; are ; the : median$", fontdict={'size':12}, color='firebrick') # Decorations red_patch = plt.plot([],[], marker="o", ms=10, ls="", mec=None, color='firebrick', label="Median") plt.legend(handles=red_patch) ax.set_title('Distribution of City Mileage by Make', fontdict={'size':22}) ax.set_xlabel('Miles Per Gallon (City)', alpha=0.7) ax.set_yticks(df.index) ax.set_yticklabels(df.manufacturer.str.title(), fontdict={'horizontalalignment': 'right'}, alpha=0.7) ax.set_xlim(1, 40) plt.xticks(alpha=0.7) plt.gca().spines["top"].set_visible(False) plt.gca().spines["bottom"].set_visible(False) plt.gca().spines["right"].set_visible(False) plt.gca().spines["left"].set_visible(False) plt.grid(axis='both', alpha=.4, linewidth=.1) plt.show()