So, here is my code:
import pandas as pd
import scipy.stats as st
import matplotlib.pyplot as plt
from matplotlib.ticker import AutoMinorLocator
from fitter import Fitter, get_common_distributions
df = pd.read_csv("project3.csv")
bins = [282.33, 594.33, 906.33, 1281.33, 15030.33, 1842.33, 2154.33, 2466.33, 2778.33, 3090.33, 3402.33]
#declaring
facecolor = '#EAEAEA'
color_bars = '#3475D0'
txt_color1 = '#252525'
txt_color2 = '#004C74'
fig, ax = plt.subplots(1, figsize=(16, 6), facecolor=facecolor)
ax.set_facecolor(facecolor)
n, bins, patches = plt.hist(df.City1, color=color_bars, bins=10)
#grid
minor_locator = AutoMinorLocator(2)
plt.gca().xaxis.set_minor_locator(minor_locator)
plt.grid(which='minor', color=facecolor, lw = 0.5)
xticks = [(bins[idx+1] + value)/2 for idx, value in enumerate(bins[:-1])]
xticks_labels = [ "{:.0f}-{:.0f}".format(value, bins[idx+1]) for idx, value in enumerate(bins[:-1])]
plt.xticks(xticks, labels=xticks_labels, c=txt_color1, fontsize=13)
#beautify
ax.tick_params(axis='x', which='both',length=0)
plt.yticks([])
ax.spines['bottom'].set_visible(False)
ax.spines['left'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['top'].set_visible(False)
for idx, value in enumerate(n):
if value > 0:
plt.text(xticks[idx], value+5, int(value), ha='center', fontsize=16, c=txt_color1)
plt.title('Histogram of rainfall in City1\n', loc = 'right', fontsize = 20, c=txt_color1)
plt.xlabel('\nCentimeters of rainfall', c=txt_color2, fontsize=14)
plt.ylabel('Frequency of occurrence', c=txt_color2, fontsize=14)
plt.tight_layout()
#plt.savefig('City1_Raw.png', facecolor=facecolor)
plt.show()
city1 = df['City1'].values
f = Fitter(city1, distributions=get_common_distributions())
f.fit()
fig = f.plot_pdf(names=None, Nbest=4, lw=1, method='sumsquare_error')
plt.show()
print(f.get_best(method = 'sumsquare_error'))
The issue is with the plots it shows. The first histogram it generates is
Next I get another graph with best fitted distributions which is
Then an output statement
{'chi2': {'df': 10.692966790090342, 'loc': 16.690849400411103, 'scale': 118.71595997157786}}
Process finished with exit code 0
I have a couple of questions. Why is chi2, the best fitted distribution not plotted on the graph?
How do I plot these distributions on top of the histograms and not separately? The hist() function in fitter library can do that but there I don't get to control the bins and so I end up getting like 100 bins with some flat looking data.
How do I solve this issue? I need to plot the best fit curve on the histogram that looks like image1. Can I use any other module/package to get the work done in similar way? This uses least squares fit but I am OK with least likelihood or log likelihood too.
Simple way of plotting things on top of each other (using some properties of the Fitter class)
import scipy.stats as st
import matplotlib.pyplot as plt
from fitter import Fitter, get_common_distributions
from scipy import stats
numberofpoints=50000
df = stats.norm.rvs( loc=1090, scale=500, size=numberofpoints)
fig, ax = plt.subplots(1, figsize=(16, 6))
n, bins, patches = ax.hist( df, bins=30, density=True)
f = Fitter(df, distributions=get_common_distributions())
f.fit()
errorlist = sorted(
[
[f._fitted_errors[dist], dist]
for dist in get_common_distributions()
]
)[:4]
for err, dist in errorlist:
ax.plot( f.x, f.fitted_pdf[dist] )
plt.show()
Using the histogram normalization, one would need to play with scaling to generalize again.
I am a little confused about how this code works:
fig, axes = plt.subplots(nrows=2, ncols=2)
plt.show()
How does the fig, axes work in this case? What does it do?
Also why wouldn't this work to do the same thing:
fig = plt.figure()
axes = fig.subplots(nrows=2, ncols=2)
There are several ways to do it. The subplots method creates the figure along with the subplots that are then stored in the ax array. For example:
import matplotlib.pyplot as plt
x = range(10)
y = range(10)
fig, ax = plt.subplots(nrows=2, ncols=2)
for row in ax:
for col in row:
col.plot(x, y)
plt.show()
However, something like this will also work, it's not so "clean" though since you are creating a figure with subplots and then add on top of them:
fig = plt.figure()
plt.subplot(2, 2, 1)
plt.plot(x, y)
plt.subplot(2, 2, 2)
plt.plot(x, y)
plt.subplot(2, 2, 3)
plt.plot(x, y)
plt.subplot(2, 2, 4)
plt.plot(x, y)
plt.show()
import matplotlib.pyplot as plt
fig, ax = plt.subplots(2, 2)
ax[0, 0].plot(range(10), 'r') #row=0, col=0
ax[1, 0].plot(range(10), 'b') #row=1, col=0
ax[0, 1].plot(range(10), 'g') #row=0, col=1
ax[1, 1].plot(range(10), 'k') #row=1, col=1
plt.show()
You can also unpack the axes in the subplots call
And set whether you want to share the x and y axes between the subplots
Like this:
import matplotlib.pyplot as plt
# fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(nrows=2, ncols=2, sharex=True, sharey=True)
fig, axes = plt.subplots(nrows=2, ncols=2, sharex=True, sharey=True)
ax1, ax2, ax3, ax4 = axes.flatten()
ax1.plot(range(10), 'r')
ax2.plot(range(10), 'b')
ax3.plot(range(10), 'g')
ax4.plot(range(10), 'k')
plt.show()
You might be interested in the fact that as of matplotlib version 2.1 the second code from the question works fine as well.
From the change log:
Figure class now has subplots method
The Figure class now has a subplots() method which behaves the same as pyplot.subplots() but on an existing figure.
Example:
import matplotlib.pyplot as plt
fig = plt.figure()
axes = fig.subplots(nrows=2, ncols=2)
plt.show()
Read the documentation: matplotlib.pyplot.subplots
pyplot.subplots() returns a tuple fig, ax which is unpacked in two variables using the notation
fig, axes = plt.subplots(nrows=2, ncols=2)
The code:
fig = plt.figure()
axes = fig.subplots(nrows=2, ncols=2)
does not work because subplots() is a function in pyplot not a member of the object Figure.
Iterating through all subplots sequentially:
fig, axes = plt.subplots(nrows, ncols)
for ax in axes.flatten():
ax.plot(x,y)
Accessing a specific index:
for row in range(nrows):
for col in range(ncols):
axes[row,col].plot(x[row], y[col])
Subplots with pandas
This answer is for subplots with pandas, which uses matplotlib as the default plotting backend.
Here are four options to create subplots starting with a pandas.DataFrame
Implementation 1. and 2. are for the data in a wide format, creating subplots for each column.
Implementation 3. and 4. are for data in a long format, creating subplots for each unique value in a column.
Tested in python 3.8.11, pandas 1.3.2, matplotlib 3.4.3, seaborn 0.11.2
Imports and Data
import seaborn as sns # data only
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
# wide dataframe
df = sns.load_dataset('planets').iloc[:, 2:5]
orbital_period mass distance
0 269.300 7.10 77.40
1 874.774 2.21 56.95
2 763.000 2.60 19.84
3 326.030 19.40 110.62
4 516.220 10.50 119.47
# long dataframe
dfm = sns.load_dataset('planets').iloc[:, 2:5].melt()
variable value
0 orbital_period 269.300
1 orbital_period 874.774
2 orbital_period 763.000
3 orbital_period 326.030
4 orbital_period 516.220
1. subplots=True and layout, for each column
Use the parameters subplots=True and layout=(rows, cols) in pandas.DataFrame.plot
This example uses kind='density', but there are different options for kind, and this applies to them all. Without specifying kind, a line plot is the default.
ax is array of AxesSubplot returned by pandas.DataFrame.plot
See How to get a Figure object, if needed.
How to save pandas subplots
axes = df.plot(kind='density', subplots=True, layout=(2, 2), sharex=False, figsize=(10, 6))
# extract the figure object; only used for tight_layout in this example
fig = axes[0][0].get_figure()
# set the individual titles
for ax, title in zip(axes.ravel(), df.columns):
ax.set_title(title)
fig.tight_layout()
plt.show()
2. plt.subplots, for each column
Create an array of Axes with matplotlib.pyplot.subplots and then pass axes[i, j] or axes[n] to the ax parameter.
This option uses pandas.DataFrame.plot, but can use other axes level plot calls as a substitute (e.g. sns.kdeplot, plt.plot, etc.)
It's easiest to collapse the subplot array of Axes into one dimension with .ravel or .flatten. See .ravel vs .flatten.
Any variables applying to each axes, that need to be iterate through, are combined with .zip (e.g. cols, axes, colors, palette, etc.). Each object must be the same length.
fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(10, 6)) # define the figure and subplots
axes = axes.ravel() # array to 1D
cols = df.columns # create a list of dataframe columns to use
colors = ['tab:blue', 'tab:orange', 'tab:green'] # list of colors for each subplot, otherwise all subplots will be one color
for col, color, ax in zip(cols, colors, axes):
df[col].plot(kind='density', ax=ax, color=color, label=col, title=col)
ax.legend()
fig.delaxes(axes[3]) # delete the empty subplot
fig.tight_layout()
plt.show()
Result for 1. and 2.
3. plt.subplots, for each group in .groupby
This is similar to 2., except it zips color and axes to a .groupby object.
fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(10, 6)) # define the figure and subplots
axes = axes.ravel() # array to 1D
dfg = dfm.groupby('variable') # get data for each unique value in the first column
colors = ['tab:blue', 'tab:orange', 'tab:green'] # list of colors for each subplot, otherwise all subplots will be one color
for (group, data), color, ax in zip(dfg, colors, axes):
data.plot(kind='density', ax=ax, color=color, title=group, legend=False)
fig.delaxes(axes[3]) # delete the empty subplot
fig.tight_layout()
plt.show()
4. seaborn figure-level plot
Use a seaborn figure-level plot, and use the col or row parameter. seaborn is a high-level API for matplotlib. See seaborn: API reference
p = sns.displot(data=dfm, kind='kde', col='variable', col_wrap=2, x='value', hue='variable',
facet_kws={'sharey': False, 'sharex': False}, height=3.5, aspect=1.75)
sns.move_legend(p, "upper left", bbox_to_anchor=(.55, .45))
Convert the axes array to 1D
Generating subplots with plt.subplots(nrows, ncols), where both nrows and ncols is greater than 1, returns a nested array of <AxesSubplot:> objects.
It’s not necessary to flatten axes in cases where either nrows=1 or ncols=1, because axes will already be 1 dimensional, which is a result of the default parameter squeeze=True
The easiest way to access the objects, is to convert the array to 1 dimension with .ravel(), .flatten(), or .flat.
.ravel vs. .flatten
flatten always returns a copy.
ravel returns a view of the original array whenever possible.
Once the array of axes is converted to 1-d, there are a number of ways to plot.
This answer is relevant to seaborn axes-level plots, which have the ax= parameter (e.g. sns.barplot(…, ax=ax[0]).
seaborn is a high-level API for matplotlib. See Figure-level vs. axes-level functions and seaborn is not plotting within defined subplots
import matplotlib.pyplot as plt
import numpy as np # sample data only
# example of data
rads = np.arange(0, 2*np.pi, 0.01)
y_data = np.array([np.sin(t*rads) for t in range(1, 5)])
x_data = [rads, rads, rads, rads]
# Generate figure and its subplots
fig, axes = plt.subplots(nrows=2, ncols=2)
# axes before
array([[<AxesSubplot:>, <AxesSubplot:>],
[<AxesSubplot:>, <AxesSubplot:>]], dtype=object)
# convert the array to 1 dimension
axes = axes.ravel()
# axes after
array([<AxesSubplot:>, <AxesSubplot:>, <AxesSubplot:>, <AxesSubplot:>],
dtype=object)
Iterate through the flattened array
If there are more subplots than data, this will result in IndexError: list index out of range
Try option 3. instead, or select a subset of the axes (e.g. axes[:-2])
for i, ax in enumerate(axes):
ax.plot(x_data[i], y_data[i])
Access each axes by index
axes[0].plot(x_data[0], y_data[0])
axes[1].plot(x_data[1], y_data[1])
axes[2].plot(x_data[2], y_data[2])
axes[3].plot(x_data[3], y_data[3])
Index the data and axes
for i in range(len(x_data)):
axes[i].plot(x_data[i], y_data[i])
zip the axes and data together and then iterate through the list of tuples.
for ax, x, y in zip(axes, x_data, y_data):
ax.plot(x, y)
Ouput
An option is to assign each axes to a variable, fig, (ax1, ax2, ax3) = plt.subplots(1, 3). However, as written, this only works in cases with either nrows=1 or ncols=1. This is based on the shape of the array returned by plt.subplots, and quickly becomes cumbersome.
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(2, 2) for a 2 x 2 array.
This option is most useful for two subplots (e.g.: fig, (ax1, ax2) = plt.subplots(1, 2) or fig, (ax1, ax2) = plt.subplots(2, 1)). For more subplots, it's more efficient to flatten and iterate through the array of axes.
You could use the following:
import numpy as np
import matplotlib.pyplot as plt
fig, _ = plt.subplots(nrows=2, ncols=2)
for i, ax in enumerate(fig.axes):
ax.plot(np.sin(np.linspace(0,2*np.pi,100) + np.pi/2*i))
Or alternatively, using the second variable that plt.subplot returns:
fig, ax_mat = plt.subplots(nrows=2, ncols=2)
for i, ax in enumerate(ax_mat.flatten()):
...
ax_mat is a matrix of the axes. It's shape is nrows x ncols.
here is a simple solution
fig, ax = plt.subplots(nrows=2, ncols=3, sharex=True, sharey=False)
for sp in fig.axes:
sp.plot(range(10))
Go with the following if you really want to use a loop:
def plot(data):
fig = plt.figure(figsize=(100, 100))
for idx, k in enumerate(data.keys(), 1):
x, y = data[k].keys(), data[k].values
plt.subplot(63, 10, idx)
plt.bar(x, y)
plt.show()
Another concise solution is:
// set up structure of plots
f, (ax1, ax2, ax3) = plt.subplots(1, 3, figsize=(20,10))
// for plot 1
ax1.set_title('Title A')
ax1.plot(x, y)
// for plot 2
ax2.set_title('Title B')
ax2.plot(x, y)
// for plot 3
ax3.set_title('Title C')
ax3.plot(x,y)
My question is based on this question:
Adjust hspace for some of the subplots
Which adjusts the top plot of a number of subplots and increases the difference in hspace. I want to increase the hspace between two plots within the subplots (in my case: between plot 3 and plot4 from the top).
Here is my example:
import numpy as np
import matplotlib.pyplot as plt
noise = np.random.rand(300)
gs_top = plt.GridSpec(9, 1, hspace=0.5)
gs_base = plt.GridSpec(9, 1, hspace=0)
fig = plt.figure()
fig.patch.set_facecolor('white')
ax0 = fig.add_subplot(gs_base[0,:])
ax1 = fig.add_subplot(gs_base[1,:])
ax2 = fig.add_subplot(gs_top[2,:])
ax3 = fig.add_subplot(gs_base[3,:])
ax4 = fig.add_subplot(gs_base[4,:])
ax5 = fig.add_subplot(gs_base[5,:])
ax0.plot(noise)
ax1.plot(noise)
ax2.plot(noise)
ax3.plot(noise)
ax4.plot(noise)
ax5.plot(noise)
In the example it is shown that the hspace increases between plot 3 and 4. However, I don't want to increase the space between plot 2 and plot 3.
How can I adjust the hspace variable only on one side?
Found the answer after manipulating google by asking with various word combinations. Found this: Stackoverflow answer
In short (dirty way):
Adding a seperate axis and make it invisible.
Example:
import numpy as np
import matplotlib.pyplot as plt
noise = np.random.rand(300)
gs_base = plt.GridSpec(7, 1, hspace=0, height_ratios=[1, 1, 1, 0.8, 1,1,1])
fig = plt.figure()
fig.patch.set_facecolor('white')
ax0 = fig.add_subplot(gs_base[0,:])
ax1 = fig.add_subplot(gs_base[1,:])
ax2 = fig.add_subplot(gs_base[2,:])
ax3 = fig.add_subplot(gs_base[3,:])
ax3.set_visible(False)
ax4 = fig.add_subplot(gs_base[4,:])
ax5 = fig.add_subplot(gs_base[5,:])
ax6 = fig.add_subplot(gs_base[6,:])
ax0.plot(noise)
ax1.plot(noise)
ax2.plot(noise)
ax4.plot(noise)
ax5.plot(noise)
ax6.plot(noise)
In long (correct way):
Couldn't figure it out for the moment.
I want to make the dates on the x- axis look more prettier, currently the dates cannot be even read. what is the best way to do it.
Below is the code and also the actual graph picture
import matplotlib.pyplot as plt
import pandas as pd
import pandas as pd
df = dataset
# gca stands for 'get current axis'
ax = plt.gca()
y1 = df['Predicted_Lower']
y2 = df['Predicted_Upper']
x = df['Date']
ax.fill_between(x,y1, y2, facecolor="#CC6666", alpha=0.7)
df.plot(kind='line',x='Date',y='Predicted_Lower',color='white',ax=ax)
df.plot(kind='line',x='Date',y='Predicted_Upper',color='white', ax=ax)
df.plot(kind='line',x='Date',y='Predicted', color='yellow', ax=ax)
df.plot(kind='line',x='Date',y='Actuals', color='green', ax=ax)
plt.xticks(rotation=45)
plt.show()
You can modify the number of labels, by settings locs and labels parameters using matplotlib.pyplot.xticks, for example get the current locs and labels and only plot one-third of them:
# ...
df.plot(kind='line',x='Date',y='Actuals', color='green', ax=ax)
locs, labels = plt.xticks()
plt.xticks(locs[::3], labels[::3], rotation=45)
plt.show()
I would greatly appreciate if you could let me know how to plot high-resolution heatmap for a large dataset with approximately 150 features.
My code is as follows:
XX = pd.read_csv('Financial Distress.csv')
y = np.array(XX['Financial Distress'].values.tolist())
y = np.array([0 if i > -0.50 else 1 for i in y])
XX = XX.iloc[:, 3:87]
df=XX
df["target_var"]=y.tolist()
target_var=["target_var"]
fig, ax = plt.subplots(figsize=(8, 6))
correlation = df.select_dtypes(include=['float64',
'int64']).iloc[:, 1:].corr()
sns.heatmap(correlation, ax=ax, vmax=1, square=True)
plt.xticks(rotation=90)
plt.yticks(rotation=360)
plt.title('Correlation matrix')
plt.tight_layout()
plt.show()
k = df.shape[1] # number of variables for heatmap
fig, ax = plt.subplots(figsize=(9, 9))
corrmat = df.corr()
# Generate a mask for the upper triangle
mask = np.zeros_like(corrmat, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True
cols = corrmat.nlargest(k, target_var)[target_var].index
cm = np.corrcoef(df[cols].values.T)
sns.set(font_scale=1.0)
hm = sns.heatmap(cm, mask=mask, cbar=True, annot=True,
square=True, fmt='.2f', annot_kws={'size': 7},
yticklabels=cols.values,
xticklabels=cols.
values)
plt.xticks(rotation=90)
plt.yticks(rotation=360)
plt.title('Annotated heatmap matrix')
plt.tight_layout()
plt.show()
It works fine but the plotted heatmap for a dataset with more than 40 features is too small.
Thanks in advance,
Adjusting the figsize and dpi worked for me.
I adapted your code and doubled the size of the heatmap to 165 x 165. The rendering takes a while, but the png looks fine. My backend is "module://ipykernel.pylab.backend_inline."
As noted in my original answer, I'm pretty sure you forgot close the figure object before creating a new one. Try plt.close("all") before fig, ax = plt.subplots() if you get wierd effects.
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
print(plt.get_backend())
# close any existing plots
plt.close("all")
df = pd.read_csv("Financial Distress.csv")
# select out the desired columns
df = df.iloc[:, 3:].select_dtypes(include=['float64','int64'])
# copy columns to double size of dataframe
df2 = df.copy()
df2.columns = "c_" + df2.columns
df3 = pd.concat([df, df2], axis=1)
# get the correlation coefficient between the different columns
corr = df3.iloc[:, 1:].corr()
arr_corr = corr.as_matrix()
# mask out the top triangle
arr_corr[np.triu_indices_from(arr_corr)] = np.nan
fig, ax = plt.subplots(figsize=(24, 18))
hm = sns.heatmap(arr_corr, cbar=True, vmin=-0.5, vmax=0.5,
fmt='.2f', annot_kws={'size': 3}, annot=True,
square=True, cmap=plt.cm.Blues)
ticks = np.arange(corr.shape[0]) + 0.5
ax.set_xticks(ticks)
ax.set_xticklabels(corr.columns, rotation=90, fontsize=8)
ax.set_yticks(ticks)
ax.set_yticklabels(corr.index, rotation=360, fontsize=8)
ax.set_title('correlation matrix')
plt.tight_layout()
plt.savefig("corr_matrix_incl_anno_double.png", dpi=300)
full figure:
zoom of top left section:
If I understand your problem correctly, I think all you have to do is increase you figure size:
f, ax = plt.subplots(figsize=(20, 20))
instead of
f, ax = plt.subplots(figsize=(9, 9))