Date Axis In Heatmap Seaborn

A little info: I'm very new to programming and this is a small part of the my first script. The goal of this particular segment is to display a seaborn heatmap with vertical depth

Solution 1:

You have to use strftime function for your date series of dataframe to plot xtick labels correctly:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime, timedelta
import random

dates = [datetime.today() - timedelta(days=x * random.getrandbits(1)) for x in xrange(25)]
df = pd.DataFrame({'depth': [0.1,0.05, 0.01, 0.005, 0.001, 0.1, 0.05, 0.01, 0.005, 0.001, 0.1, 0.05, 0.01, 0.005, 0.001, 0.1, 0.05, 0.01, 0.005, 0.001, 0.1, 0.05, 0.01, 0.005, 0.001],\
 'date': dates,\
 'value': [-4.1808639999999997, -9.1753490000000006, -11.408113999999999, -10.50245, -8.0274750000000008, -0.72260200000000008, -6.9963940000000004, -10.536339999999999, -9.5440649999999998, -7.1964070000000007, -0.39225599999999999, -6.6216390000000001, -9.5518009999999993, -9.2924690000000005, -6.7605589999999998, -0.65214700000000003, -6.8852289999999989, -9.4557760000000002, -8.9364629999999998, -6.4736289999999999, -0.96481800000000006, -6.051482, -9.7846860000000007, -8.5710630000000005, -6.1461209999999999]})
pivot = df.pivot(index='depth', columns='date', values='value')

sns.set()
ax = sns.heatmap(pivot)
ax.set_xticklabels(df['date'].dt.strftime('%d-%m-%Y'))
plt.xticks(rotation=-90)

plt.show()

Solution 2:

Example with standard heatmap datetime labels

import pandas as pd
import seaborn as sns

dates = pd.date_range('2019-01-01', '2020-12-01')

df = pd.DataFrame(np.random.randint(0, 100, size=(len(dates), 4)), index=dates)

sns.heatmap(df)

We can create some helper classes/functions to get to some better looking labels and placement. AxTransformer enables conversion from data coordinates to tick locations, set_date_ticks allows custom date ranges to be applied to plots.

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from collections.abc import Iterable
from sklearn import linear_model

classAxTransformer:
    def__init__(self, datetime_vals=False):
        self.datetime_vals = datetime_vals
        self.lr = linear_model.LinearRegression()
        
        returndefprocess_tick_vals(self, tick_vals):
        ifnotisinstance(tick_vals, Iterable) orisinstance(tick_vals, str):
            tick_vals = [tick_vals]
            
        if self.datetime_vals == True:
            tick_vals = pd.to_datetime(tick_vals).astype(int).values
            
        tick_vals = np.array(tick_vals)
            
        return tick_vals
    
    deffit(self, ax, axis='x'):
        axis = getattr(ax, f'get_{axis}axis')()
        
        tick_locs = axis.get_ticklocs()
        tick_vals = self.process_tick_vals([label._text for label in axis.get_ticklabels()])
        
        self.lr.fit(tick_vals.reshape(-1, 1), tick_locs)
        
        returndeftransform(self, tick_vals):        
        tick_vals = self.process_tick_vals(tick_vals)
        tick_locs = self.lr.predict(np.array(tick_vals).reshape(-1, 1))
        
        return tick_locs
    
defset_date_ticks(ax, start_date, end_date, axis='y', date_format='%Y-%m-%d', **date_range_kwargs):
    dt_rng = pd.date_range(start_date, end_date, **date_range_kwargs)

    ax_transformer = AxTransformer(datetime_vals=True)
    ax_transformer.fit(ax, axis=axis)
    
    getattr(ax, f'set_{axis}ticks')(ax_transformer.transform(dt_rng))
    getattr(ax, f'set_{axis}ticklabels')(dt_rng.strftime(date_format))

    ax.tick_params(axis=axis, which='both', bottom=True, top=False, labelbottom=True)
    
    return ax

These provide us a lot of flexibility, e.g.

fig, ax = plt.subplots(dpi=150)

sns.heatmap(df, ax=ax)

set_date_ticks(ax, '2019-01-01', '2020-12-01', freq='3MS')

or if you really want to get weird you can do stuff like

fig, ax = plt.subplots(dpi=150)

sns.heatmap(df, ax=ax)

set_date_ticks(ax, '2019-06-01', '2020-06-01', freq='2MS', date_format='%b `%y')

For your specific example you'll have to pass axis='x' to set_date_ticks

Solution 3:

• First, the 'date' column must be converted to a datetime dtype with pandas.to_datetime
• If the desired result is to only have the dates (without time), then the easiest solution is to use the .dt accessor to extract the .date component. Alternative, use dt.strftime to set a specific string format.
  • strftime() and strptime() Format Codes
  • df.date.dt.strftime('%H:%M') would extract hours and minutes into a string like '14:29'
  • In the example below, the extracted date is assigned to the same column, but the value can also be assigned as a new column.
• pandas.DataFrame.pivot_table is used to aggregate a function if there are multiple values in a column for each index, pandas.DataFrame.pivot should be used if there is only a single value.
  • This is better than .groupby because the dataframe is correctly shaped to be easily plotted.
• Tested in python 3.8.11, pandas 1.3.2, matplotlib 3.4.3, seaborn 0.11.2

import pandas as pd
import numpy as np
import seaborn as sns

# create sample data
dates = [f'2016-08-{d}T00:00:00.000000000'for d inrange(9, 26, 2)] + ['2016-09-09T00:00:00.000000000']
depths = np.arange(1.25, 5.80, 0.25)
np.random.seed(365)
p1 = np.random.dirichlet(np.ones(10), size=1)[0]  # random probabilities for random.choice
p2 = np.random.dirichlet(np.ones(19), size=1)[0]  # random probabilities for random.choice
data = {'date': np.random.choice(dates, size=1000, p=p1), 'depth': np.random.choice(depths, size=1000, p=p2), 'capf': np.random.normal(0.3, 0.05, size=1000)}
df = pd.DataFrame(data)

# display(df.head())
                            date  depth      capf
02016-08-19T00:00:00.0000000004.750.33923312016-08-19T00:00:00.0000000003.000.37039522016-08-21T00:00:00.0000000005.750.33289532016-08-23T00:00:00.0000000001.750.23754342016-08-23T00:00:00.0000000005.750.272067# make sure the date column is converted to a datetime dtype
df.date = pd.to_datetime(df.date)

# extract only the date component of the date column
df.date = df.date.dt.date

# reshape the data for heatmap; if there's no need to aggregate a function, then use .pivot(...)
dfp = df.pivot_table(index='depth', columns='date', values='capf', aggfunc='mean')

# display(dfp.head())
date   2016-08-09  2016-08-112016-08-132016-08-152016-08-172016-08-192016-08-212016-08-232016-08-252016-09-09
depth                                                                                                                        
1.500.334661         NaN         NaN    0.3026700.3141860.3252570.3136450.263135         NaN         NaN
1.750.3054880.3030050.4101240.2990950.3138990.2807320.2757580.260641         NaN    0.3180992.000.3223120.274105         NaN    0.3196060.2689840.3684490.3115170.309923         NaN    0.3061622.250.2899590.315081         NaN    0.3022020.3062860.3398090.2925460.3142250.263875         NaN
2.500.3142270.296968         NaN    0.3127050.3337970.2995560.3271870.326958         NaN         NaN

# plot
sns.heatmap(dfp, cmap='GnBu')

Solution 4:

I had a similar problem, but the date was the index. I've just converted the date to string (pandas 1.0) before plotting and it worked for me.

heat['date'] = heat.date.astype('string')