Aligning two y-axes at 0 with the same number of tickers dynamically-CodePudding

I am able to plot a seaborn barplot and lineplot on the the same plot with the axes aligned at 0 and the same number of tickers. However, I cannot cut off any empty spaces dynamically. The code for the plot can be found below. What I would like to end up with is the same graph I have attached, but with the tickers ending at -49.3 and -13.63 (to get rid of any blank spaces). I do not want to hard code it, it needs to be dynamic so that it is able to adjust for any input data. Also, both axes still need to align at 0 and have the same number of tickers.

import numpy as np
import pandas as pd
import math
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.dates as md
import matplotlib.ticker as ticker
from datetime import datetime, timedelta

# create dataframes that will be used
date_today = datetime.now()
days = pd.date_range(date_today, date_today   timedelta(1000), freq='D')

np.random.seed(seed=1111)
data_a = np.random.randint(-10, high=20, size=len(days))
data_b = np.random.randint(-30, high=70, size=len(days))

a = pd.DataFrame({'date': days, 'a': data_a})
a = a.set_index('date')

b = pd.DataFrame({'date': days, 'b': data_b})
b = b.set_index('date')

# result dataframe which will be used for the plotting 
result = pd.concat([a, b], axis=1)

# make sure only the dates are being used 
result = result.reset_index()
result['date'] = result['date'].dt.date
result = result.set_index('date')

# set- up for the plot
matplotlib.rc_file_defaults()
ax1 = sns.set_style(style=None, rc=None)
fig, ax1 = plt.subplots(figsize=(12,6))
ax2 = ax1.twinx()

# bar plot
result_date = result.copy()
result_date = result_date.reset_index()

b_plot = sns.barplot(data = result_date, x=result_date.iloc[:, 0], y=result_date.iloc[:, 2], ax=ax1)

# pointplot
a_plot = sns.pointplot(data=result, x=result.index, y=result.iloc[:, 0], color="black", ax=ax2, markers = 'o', scale=0.4)

# set the x tickers to be those of the bar plot
ax1.set_xticks(np.arange(len(result_date)))
ax1.set_xticklabels(result_date.date.apply(lambda x: str(x.year)))
ax1.xaxis.set_major_locator(ticker.AutoLocator())


# to align the axes and make them start at 0
max1 = np.nanmax(np.abs(ax1.get_ybound())) # in case you have nan values
max2 = np.nanmax(np.abs(ax2.get_ybound()))
nticks = 7 #or other odd number
ax1.set_yticks(np.linspace(-max1, max1, nticks))
ax2.set_yticks(np.linspace(-max2, max2, nticks))

plot

EDIT: Here is another method I tried using answers from other posts, but it still does not achieve what I want:

import numpy as np
import pandas as pd
import math
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.dates as md
import matplotlib.ticker as ticker
from datetime import datetime, timedelta

# create dataframes that will be used
date_today = datetime.now()
days = pd.date_range(date_today, date_today   timedelta(1000), freq='D')

np.random.seed(seed=1111)
data_a = np.random.randint(-10, high=20, size=len(days))
data_b = np.random.randint(-30, high=70, size=len(days))

a = pd.DataFrame({'date': days, 'a': data_a})
a = a.set_index('date')

b = pd.DataFrame({'date': days, 'b': data_b})
b = b.set_index('date')

# result dataframe which will be used for the plotting 
result = pd.concat([a, b], axis=1)

# make sure only the dates are being used 
result = result.reset_index()
result['date'] = result['date'].dt.date
result = result.set_index('date')

# set- up for the plot
matplotlib.rc_file_defaults()
ax1 = sns.set_style(style=None, rc=None)
fig, ax1 = plt.subplots(figsize=(12,6))
ax2 = ax1.twinx()

# bar plot
result_date = result.copy()
result_date = result_date.reset_index()

b_plot = sns.barplot(data = result_date, x=result_date.iloc[:, 0], y=result_date.iloc[:, 2], ax=ax1)

# pointplot
a_plot = sns.pointplot(data=result, x=result.index, y=result.iloc[:, 0], color="black", ax=ax2, markers = 'o', scale=0.4)

# set the x tickers to be those of the bar plot
ax1.set_xticks(np.arange(len(result_date)))
ax1.set_xticklabels(result_date.date.apply(lambda x: str(x.year)))
ax1.xaxis.set_major_locator(ticker.AutoLocator())


ax1_ylims = ax1.axes.get_ylim()           # Find y-axis limits set by the plotter
ax1_yratio = ax1_ylims[0] / ax1_ylims[1]  # Calculate ratio of lowest limit to highest limit

ax2_ylims = ax2.axes.get_ylim()           # Find y-axis limits set by the plotter
ax2_yratio = ax2_ylims[0] / ax2_ylims[1]  # Calculate ratio of lowest limit to highest limit


# If the plot limits ratio of plot 1 is smaller than plot 2, the first data set has
# a wider range range than the second data set. Calculate a new low limit for the
# second data set to obtain a similar ratio to the first data set.
# Else, do it the other way around

if ax1_yratio < ax2_yratio: 
    ax2.set_ylim(bottom = ax2_ylims[1]*ax1_yratio)
    nticks = len(ax1.yaxis.get_ticklabels()) # number of ticks for the wider axis 
    ax2.set_yticks(np.linspace(ax2.get_ylim()[0], ax2.get_ylim()[-1], nticks))
    
    
else:
    ax1.set_ylim(bottom = ax1_ylims[1]*ax2_yratio)
    nticks = len(ax2.yaxis.get_ticklabels()) # number of ticks for the wider axis 
    ax1.set_yticks(np.linspace(ax1.get_ylim()[0], ax1.get_ylim()[-1], nticks))

plot 2

CodePudding user response：

What about:

import numpy as np
import pandas as pd
import math
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.dates as md
import matplotlib.ticker as ticker
from datetime import datetime, timedelta

# create dataframes that will be used
date_today = datetime.now()
days = pd.date_range(date_today, date_today   timedelta(1000), freq='D')

np.random.seed(seed=1111)
data_a = np.random.randint(-10, high=20, size=len(days))
data_b = np.random.randint(-30, high=70, size=len(days))

a = pd.DataFrame({'date': days, 'a': data_a})
a = a.set_index('date')

b = pd.DataFrame({'date': days, 'b': data_b})
b = b.set_index('date')

# result dataframe which will be used for the plotting
result = pd.concat([a, b], axis=1)

# make sure only the dates are being used
result = result.reset_index()
result['date'] = result['date'].dt.date
result = result.set_index('date')

# set- up for the plot
matplotlib.rc_file_defaults()
sns.set_style(style=None, rc=None)
fig, ax1 = plt.subplots(figsize=(12,6))
ax2 = ax1.twinx()

# bar plot
result_date = result.reset_index()

b_plot = sns.barplot(data = result_date, x=result_date.iloc[:, 0], y=result_date.iloc[:, 2], ax=ax1)

# pointplot
a_plot = sns.pointplot(data=result, x=result.index, y=result.iloc[:, 0], color="black", ax=ax2, markers = 'o', scale=0.4)

# set the x tickers to be those of the bar plot
ax1.set_xticks(np.arange(len(result_date)))
ax1.set_xticklabels(result_date.date.apply(lambda x: str(x.year)))
ax1.xaxis.set_major_locator(ticker.AutoLocator())

# get the original ylims (before setting the yticks)
ax1_ylims = ax1.get_ylim()
ax1_yratio = ax1_ylims[0] / ax1_ylims[1]  # Calculate ratio of lowest limit to highest limit
ax2_ylims = ax2.get_ylim()
ax2_yratio = ax2_ylims[0] / ax2_ylims[1]  # Calculate ratio of lowest limit to highest limit

# to align the axes and make them start at 0
max1 = np.nanmax(np.abs(ax1.get_ybound())) # in case you have nan values
max2 = np.nanmax(np.abs(ax2.get_ybound()))
nticks = 7 #or other odd number
ax1.set_yticks(np.linspace(-max1, max1, nticks))
ax2.set_yticks(np.linspace(-max2, max2, nticks))

# If the plot limits ratio of plot 1 is smaller than plot 2, the first data set has
# a wider range range than the second data set. Calculate a new low limit for the
# second data set to obtain a similar ratio to the first data set.
# Else, do it the other way around
if ax1_yratio < ax2_yratio:
    ax2.set_ylim(bottom=ax2_ylims[1] * ax1_yratio)
    ax1.set_ylim(ax1_ylims)
else:
    ax1.set_ylim(bottom=ax1_ylims[1] * ax2_yratio)
    ax2.set_ylim(ax2_ylims)
plt.show()

CodePudding user response：

Here is the solution I have come up with which works for datasets with different ranges. It also ensures the tickers have equal spaces between them. Please let me know if there is a way to make it more concise.

import numpy as np
import pandas as pd
import math
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.dates as md
import matplotlib.ticker as ticker
from datetime import datetime, timedelta

# create dataframes that will be used
date_today = datetime.now()
days = pd.date_range(date_today, date_today   timedelta(1000), freq='D')

np.random.seed(seed=1111)
data_a = np.random.randint(-9, high=30, size=len(days))
data_b = np.random.randint(-20, high=70, size=len(days))

a = pd.DataFrame({'date': days, 'a': data_a})
a = a.set_index('date')

b = pd.DataFrame({'date': days, 'b': data_b})
b = b.set_index('date')

# result dataframe which will be used for the plotting
result = pd.concat([a, b], axis=1)

# make sure only the dates are being used
result = result.reset_index()
result['date'] = result['date'].dt.date
result = result.set_index('date')

# set- up for the plot
matplotlib.rc_file_defaults()
sns.set_style(style=None, rc=None)
fig, ax1 = plt.subplots(figsize=(12,6))
ax2 = ax1.twinx()

# bar plot
result_date = result.reset_index()

b_plot = sns.barplot(data = result_date, x=result_date.iloc[:, 0], y=result_date.iloc[:, 2], ax=ax1)

# pointplot
a_plot = sns.pointplot(data=result, x=result.index, y=result.iloc[:, 0], color="black", ax=ax2, markers = 'o', scale=0.4)

# set the x tickers to be those of the bar plot
ax1.set_xticks(np.arange(len(result_date)))
ax1.set_xticklabels(result_date.date.apply(lambda x: str(x.year)))
ax1.xaxis.set_major_locator(ticker.AutoLocator())

# get the max and min values for both plot datasets 
max_value_1 = np.max(result_date.iloc[:, 2])
min_value_1 = np.min(result_date.iloc[:, 2])
max_value_2 = np.max(result.iloc[:, 0])
min_value_2 = np.min(result.iloc[:, 0])

# to align the axes and make them start at 0
max1 = np.nanmax(np.abs(ax1.get_ybound())) # in case you have nan values
max2 = np.nanmax(np.abs(ax2.get_ybound()))
nticks = 7 #or other odd number
ax1.set_yticks(np.linspace(-max1, max1, nticks))
ax2.set_yticks(np.linspace(-max2, max2, nticks))

# y axis value arrays going from -ve to  ve values
ax1_y_ticks = ax1.get_yticks() 
ax2_y_ticks = ax2.get_yticks()

# create empty lists for the indexes of the upper and lower elements of the two y-ranges
ax1_lower_elements = [] # pick last value (first ticker just below the lowest value in the range)
ax1_upper_elements = [] # pick first value (first ticker just above the highest value in the range)
ax2_lower_elements = [] # pick last value
ax2_upper_elements = [] # pick first value

for i in range(len(ax1_y_ticks)):
    if ax1_y_ticks[i] <= min_value_1:
        ax1_lower_elements.append(i)

    if ax1_y_ticks[i] >= max_value_1:
        ax1_upper_elements.append(i)

for i in range(len(ax2_y_ticks)):
    if ax2_y_ticks[i] <= min_value_2:
        ax2_lower_elements.append(i)

    if ax2_y_ticks[i] >= max_value_2:
        ax2_upper_elements.append(i)        

# get the indexs for the upper and lower limits of the y-axes
ax1_lower_ticker_element = ax1_lower_elements[-1]
ax1_upper_ticker_element = ax1_upper_elements[0]
ax2_lower_ticker_element = ax2_lower_elements[-1]
ax2_upper_ticker_element = ax2_upper_elements[0]


# determine which upper and lower indexes should be used
if ax1_lower_ticker_element <= ax2_lower_ticker_element: 
    lower_ticker_element = ax1_lower_ticker_element
else: 
    lower_ticker_element = ax2_lower_ticker_element

if ax1_upper_ticker_element <= ax2_upper_ticker_element: 
    upper_ticker_element = ax2_upper_ticker_element
else: 
    upper_ticker_element = ax1_upper_ticker_element
    
# the indexes to be used as a list
new_y_ticker_elements = []
for i in range (len(ax1_y_ticks)):
    if ((i >= lower_ticker_element) & (i <= upper_ticker_element)):
        new_y_ticker_elements.append(i)      
        
# setting y-axis for ax1 
ax1_rng = []
for i in range(len(new_y_ticker_elements)):
    ax1_rng.append(ax1_y_ticks[new_y_ticker_elements[i]])
ax1.set_yticks(ax1_rng)
ax1.set_ylim(bottom=ax1_rng[0], top=ax1_rng[-1])

# setting y-axis for ax2
ax2_rng = []
for i in range(len(new_y_ticker_elements)):
    ax2_rng.append(ax2_y_ticks[new_y_ticker_elements[i]])
ax2.set_yticks(ax2_rng)
ax2.set_ylim(bottom=ax2_rng[0], top=ax2_rng[-1])

Here is the final plot plot