50个常用统计图表代码总结(9）
41. Plotting with different scales using secondary Y axis
If you want to show two time series that measures two different quantities at the same point in time, you can plot the second series againt the secondary Y axis on the right.
Learn to draw a multiple axis time series using this free video tutorial.
# Import Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/economics.csv")
x = df['date']
y1 = df['psavert']
y2 = df['unemploy']
# Plot Line1 (Left Y Axis)
fig, ax1 = plt.subplots(1,1,figsize=(16,9), dpi=80)
ax1.plot(x, y1, color='tab:red')
# Plot Line2 (Right Y Axis)
ax2 = ax1.twinx()# instantiate a second axes that shares the same x-axis
ax2.plot(x, y2, color='tab:blue')
# Decorations
# ax1 (left Y axis)
ax1.set_xlabel('Year', fontsize=20)
ax1.tick_params(axis='x', rotation=0, labelsize=12)
ax1.set_ylabel('Personal Savings Rate', color='tab:red', fontsize=20)
ax1.tick_params(axis='y', rotation=0, labelcolor='tab:red')
ax1.grid(alpha=.4)
# ax2 (right Y axis)
ax2.set_ylabel("# Unemployed (1000's)", color='tab:blue', fontsize=20)
ax2.tick_params(axis='y', labelcolor='tab:blue')
ax2.set_xticks(np.arange(0, len(x),60))
ax2.set_xticklabels(x[::60], rotation=90, fontdict={'fontsize':10})
ax2.set_title("Personal Savings Rate vs Unemployed: Plotting in Secondary Y Axis", fontsize=22)
fig.tight_layout()
plt.show()
42. Time Series with Error Bands
Time series with error bands can be constructed if you have a time series dataset with multiple observations for each time point (date / timestamp). Below you can see a couple of examples based on the orders coming in at various times of the day. And another example on the number of orders arriving over a duration of 45 days.
In this approach, the mean of the number of orders is denoted by the white line. And a 95% confidence bands are computed and drawn around the mean.
from scipy.stats import sem
# Import Data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/user_orders_hourofday.csv")
df_mean = df.groupby('order_hour_of_day').quantity.mean()
df_se = df.groupby('order_hour_of_day').quantity.apply(sem).mul(1.96)
# Plot
plt.figure(figsize=(16,10), dpi=80)
plt.ylabel("# Orders", fontsize=16)
x = df_mean.index
plt.plot(x, df_mean, color="white", lw=2)
plt.fill_between(x, df_mean - df_se, df_mean + df_se, color="#3F5D7D")
# Decorations
# Lighten borders
plt.gca().spines["top"].set_alpha(0)
plt.gca().spines["bottom"].set_alpha(1)
plt.gca().spines["right"].set_alpha(0)
plt.gca().spines["left"].set_alpha(1)
plt.xticks(x[::2],], fontsize=12)
plt.title("User Orders by Hour of Day (95% confidence)", fontsize=22)
plt.xlabel("Hour of Day")
s, e = plt.gca().get_xlim()
plt.xlim(s, e)
# Draw Horizontal Tick lines
for y in range(8,20,2):
plt.hlines(y, xmin=s, xmax=e, colors='black', alpha=0.5, linestyles="--", lw=0.5)
plt.show()
"Data Source: <a href="https://www.kaggle.com/olistbr/brazilian-ecommerce#olist_orders_dataset.csv" target="_blank">https://www.kaggle.com/olistbr/brazilian-ecommerce#olist_orders_dataset.csv</a>"
from dateutil.parser import parse
from scipy.stats import sem
# Import Data
df_raw = pd.read_csv('https://raw.githubusercontent.com/selva86/datasets/master/orders_45d.csv',
parse_dates=['purchase_time','purchase_date'])
# Prepare Data: Daily Mean and SE Bands
df_mean = df_raw.groupby('purchase_date').quantity.mean()
df_se = df_raw.groupby('purchase_date').quantity.apply(sem).mul(1.96)
# Plot
plt.figure(figsize=(16,10), dpi=80)
plt.ylabel("# Daily Orders", fontsize=16)
x =
plt.plot(x, df_mean, color="white", lw=2)
plt.fill_between(x, df_mean - df_se, df_mean + df_se, color="#3F5D7D")
# Decorations
# Lighten borders
plt.gca().spines["top"].set_alpha(0)
plt.gca().spines["bottom"].set_alpha(1)
plt.gca().spines["right"].set_alpha(0)
plt.gca().spines["left"].set_alpha(1)
plt.xticks(x[::6],], fontsize=12)
plt.title("Daily Order Quantity of Brazilian Retail with Error Bands (95% confidence)", fontsize=20)
# Axis limits
s, e = plt.gca().get_xlim()
plt.xlim(s, e-2)
plt.ylim(4,10)
# Draw Horizontal Tick lines
for y in range(5,10,1):
plt.hlines(y, xmin=s, xmax=e, colors='black', alpha=0.5, linestyles="--", lw=0.5)
plt.show()
43. Stacked Area Chart
Stacked area chart gives an visual representation of the extent of contribution from multiple time series so that it is easy to compare against each other.
# Import Data
df = pd.read_csv('https://raw.githubusercontent.com/selva86/datasets/master/nightvisitors.csv')
# Decide Colors
mycolors =['tab:red','tab:blue','tab:green','tab:orange','tab:brown','tab:grey','tab:pink','tab:olive']
# Draw Plot and Annotate
fig, ax = plt.subplots(1,1,figsize=(16,9), dpi=80)
columns = df.columns
labs = columns.values.tolist()
# Prepare data
x= df['yearmon'].values.tolist()
y0 = df].values.tolist()
y1 = df].values.tolist()
y2 = df].values.tolist()
y3 = df].values.tolist()
y4 = df].values.tolist()
y5 = df].values.tolist()
y6 = df].values.tolist()
y7 = df].values.tolist()
y = np.vstack()
# Plot for each column
labs = columns.values.tolist()
ax = plt.gca()
ax.stackplot(x, y, labels=labs, colors=mycolors, alpha=0.8)
# Decorations
ax.set_title('Night Visitors in Australian Regions', fontsize=18)
ax.set(ylim=)
ax.legend(fontsize=10, ncol=4)
plt.xticks(x[::5], fontsize=10, horizontalalignment='center')
plt.yticks(np.arange(10000,100000,20000), fontsize=10)
plt.xlim(x, x[-1])
# Lighten borders
plt.gca().spines["top"].set_alpha(0)
plt.gca().spines["bottom"].set_alpha(.3)
plt.gca().spines["right"].set_alpha(0)
plt.gca().spines["left"].set_alpha(.3)
plt.show()
44. Area Chart UnStacked
An unstacked area chart is used to visualize the progress (ups and downs) of two or more series with respect to each other. In the chart below, you can clearly see how the personal savings rate comes down as the median duration of unemployment increases. The unstacked area chart brings out this phenomenon nicely.
# Import Data
df = pd.read_csv("https://github.com/selva86/datasets/raw/master/economics.csv")
# Prepare Data
x = df['date'].values.tolist()
y1 = df['psavert'].values.tolist()
y2 = df['uempmed'].values.tolist()
mycolors =['tab:red','tab:blue','tab:green','tab:orange','tab:brown','tab:grey','tab:pink','tab:olive']
columns =['psavert','uempmed']
# Draw Plot
fig, ax = plt.subplots(1,1, figsize=(16,9), dpi=80)
ax.fill_between(x, y1=y1, y2=0, label=columns, alpha=0.5, color=mycolors, linewidth=2)
ax.fill_between(x, y1=y2, y2=0, label=columns, alpha=0.5, color=mycolors, linewidth=2)
# Decorations
ax.set_title('Personal Savings Rate vs Median Duration of Unemployment', fontsize=18)
ax.set(ylim=)
ax.legend(loc='best', fontsize=12)
plt.xticks(x[::50], fontsize=10, horizontalalignment='center')
plt.yticks(np.arange(2.5,30.0,2.5), fontsize=10)
plt.xlim(-10, x[-1])
# Draw Tick lines
for y in np.arange(2.5,30.0,2.5):
plt.hlines(y, xmin=0, xmax=len(x), colors='black', alpha=0.3, linestyles="--", lw=0.5)
# Lighten borders
plt.gca().spines["top"].set_alpha(0)
plt.gca().spines["bottom"].set_alpha(.3)
plt.gca().spines["right"].set_alpha(0)
plt.gca().spines["left"].set_alpha(.3)
plt.show()
45. Calendar Heat Map
Calendar map is an alternate and a less preferred option to visualise time based data compared to a time series. Though can be visually appealing, the numeric values are not quite evident. It is however effective in picturising the extreme values and holiday effects nicely.
import matplotlib as mpl
import calmap
# Import Data
df = pd.read_csv("https://raw.githubusercontent.com/selva86/datasets/master/yahoo.csv", parse_dates=['date'])
df.set_index('date', inplace=True)
# Plot
plt.figure(figsize=(16,10), dpi=80)
calmap.calendarplot(df['2014']['VIX.Close'], fig_kws={'figsize':(16,10)}, yearlabel_kws={'color':'black','fontsize':14}, subplot_kws={'title':'Yahoo Stock Prices'})
plt.show()
文章来源于微信公众号：自学气象人
页:
[1]