Develop Reference

I want to make vertical bars with values on top of each bar

the plot is horizontal without values I tried this code
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
g = sns.barplot(
x="score",
y="subject",
hue="pipeline",
#col="dataset",
data=results,
palette="viridis",
)
I tried this for values
ax = g.axes[0, 0]
ax.bar_label(ax.containers[0])
I had this error
'AxesSubplot' object is not subscriptable

You can try this by using the bar chart from pandas. If you want the plot horizontal use .barh If you provide a snippet from your df it would be easier to fit the data, though. If you want to use a hue you can just pivot your data to the right format.
ax = (df
.plot.bar(#insert your x and y
)
)
for c in ax.containers:
# Optional: if the segment is small or 0, customize the labels
labels = [v.get_height() if v.get_height() > 0 else '' for v in c]
# remove the labels parameter if it's not needed for customized labels
ax.bar_label(c, labels=labels, label_type='edge')

How to add multiple custom ticks to seaborn boxplot

I generated a boxplot using seaborn. On the x axis, I would like to have, both the number of days (20, 25, 32) and the actual dates they refer to (2022-05-08, 2022-05-13, 2022-05-20).
I found a potential solution at the following link add custom tick with matplotlib. I'm trying to adapt it to my problem but I could only get the number of days or the dates, not both.
I really would appreciate any help. Thank you in advance for your time.
Please, find below my code and the desired output.
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
df = pd.DataFrame({'nb_days':[20,20,20,25,25,20,32,32,25,32,32],
'Dates':['2022-05-08','2022-05-08','2022-05-08','2022-05-13','2022-05-13','2022-05-08','2022-05-20','2022-05-20','2022-05-13','2022-05-20','2022-05-20'],
'score':[3,3.5,3.4,2,2.2,3,5,5.2,4,4.3,5]})
df['Dates'] = df['Dates'].apply(pd.to_datetime)
tick_label = dict(zip(df['nb_days'],df['Dates'].apply(lambda x: x.strftime('%Y-%m-%d')))) #My custom xtick label
#Plot
fig,ax = plt.subplots(figsize=(6,6))
ax = sns.boxplot(x='nb_days',y='score',data=df,color=None)
# iterate over boxes to change color
for i,box in enumerate(ax.artists):
box.set_edgecolor('red')
box.set_facecolor('white')
sns.stripplot(x='nb_days',y='score',data=df,color='black')
ticks = sorted(df['nb_days'].unique())
labels = [tick_label.get(t, ticks[i]) for i,t in enumerate(ticks)]
ax.set_xticklabels(labels)
plt.tight_layout()
plt.show()
plt.close()
Here is the desired output.

You can do that by adding these lines in place of ax.set_xticklabels(labels)
new_labels=["{}\n{}".format(a_, b_) for a_, b_ in zip(ticks, labels)]
ax.set_xticklabels(new_labels)
Output

Try this:
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
df = pd.DataFrame({'nb_days':[20,20,20,25,25,20,32,32,25,32,32],
'Dates':['2022-05-08','2022-05-08','2022-05-08','2022-05-13','2022-05-13','2022-05-08','2022-05-20','2022-05-20','2022-05-13','2022-05-20','2022-05-20'],
'score':[3,3.5,3.4,2,2.2,3,5,5.2,4,4.3,5]})
df['Dates'] = df['Dates'].apply(pd.to_datetime)
tick_label = dict(zip(df['nb_days'],df['Dates'].apply(lambda x: x.strftime('%Y-%m-%d')))) #My custom xtick label
#Plot
fig,ax = plt.subplots(figsize=(6,6))
ax = sns.boxplot(x='nb_days',y='score',data=df,color=None)
# iterate over boxes to change color
for i,box in enumerate(ax.artists):
box.set_edgecolor('red')
box.set_facecolor('white')
sns.stripplot(x='nb_days',y='score',data=df,color='black')
ticks = sorted(df['nb_days'].unique())
labels = ["{}\n".format(t)+tick_label.get(t, ticks[i]) for i, t in enumerate(ticks)]
ax.set_xticklabels(labels)
plt.tight_layout()
plt.show()
plt.close()

Fix x-axis scale seaborn factorplot

I'm attempting to make a figure that shows two plots, with each plot separated based on a set of categorical data. However, although I can make the graph, I cant figure out how to get the x-axis to be properly spaced.
I want the x-axis to start before the first value (want axis to start at 60 [first value = 63]) and end after the last (want axis to end at 95 [last value = 92.1]), with xticks going up in 5's.
Any help is much appreciated! Thanks in advance!
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.axes
import seaborn as sns
Temperature = [63.0,63.3,63.6,63.9,64.2,64.5,64.8,65.2,65.5,65.8,66.1,66.4,66.7,67.0,67.3,67.7,68.0,68.3,68.6,68.9,69.2,69.5,69.9,70.2,70.5,70.8,71.1,71.4,71.8,72.1,72.4,72.7,73.0,73.4,73.7,74.0,74.3,74.6,74.9,75.2,75.6,75.9,76.2,76.5,76.9,77.2,77.5,77.8,78.1,78.5,78.8,79.1,79.4,79.7,80.1,80.4,80.7,81.0,81.3,81.6,81.9,82.3,82.6,82.9,83.2,83.5,83.8,84.1,84.4,84.8,85.1,85.4,85.7,86.0,86.3,86.6,86.9,87.2,87.5,87.8,88.1,88.4,88.7,89.0,89.3,89.6,89.8,90.1,90.4,90.7,91.0,91.2,91.5,91.8,92.1,63.0,63.3,63.6,63.9,64.2,64.5,64.8,65.2,65.5,65.8,66.1,66.4,66.7,67.0,67.3,67.7,68.0,68.3,68.6,68.9,69.2,69.5,69.9,70.2,70.5,70.8,71.1,71.4,71.8,72.1,72.4,72.7,73.0,73.4,73.7,74.0,74.3,74.6,74.9,75.2,75.6,75.9,76.2,76.5,76.9,77.2,77.5,77.8,78.1,78.5,78.8,79.1,79.4,79.7,80.1,80.4,80.7,81.0,81.3,81.6,81.9,82.3,82.6,82.9,83.2,83.5,83.8,84.1,84.4,84.8,85.1,85.4,85.7,86.0,86.3,86.6,86.9,87.2,87.5,87.8,88.1,88.4,88.7,89.0,89.3,89.6,89.8,90.1,90.4,90.7,91.0,91.2,91.5,91.8,92.1]
Derivative = [0.0495,0.0507,0.0525,0.0548,0.0570,0.0579,0.0579,0.0574,0.0574,0.0576,0.0581,0.0587,0.0593,0.0592,0.0584,0.0580,0.0579,0.0580,0.0582,0.0588,0.0592,0.0594,0.0588,0.0581,0.0578,0.0579,0.0580,0.0579,0.0582,0.0581,0.0579,0.0574,0.0571,0.0563,0.0548,0.0538,0.0536,0.0540,0.0544,0.0551,0.0556,0.0551,0.0542,0.0535,0.0536,0.0542,0.0564,0.0623,0.0748,0.0982,0.1360,0.1897,0.2550,0.3228,0.3807,0.4177,0.4248,0.3966,0.3365,0.2558,0.1713,0.0971,0.0438,0.0140,0.0034,0.0028,0.0048,0.0058,0.0057,0.0050,0.0042,0.0038,0.0039,0.0041,0.0038,0.0031,0.0023,0.0017,0.0014,0.0012,0.0015,0.0019,0.0020,0.0018,0.0017,0.0015,0.0014,0.0014,0.0015,0.0014,0.0013,0.0011,0.0007,0.0004,0.0011,0.0105,0.0100,0.0096,0.0090,0.0084,0.0081,0.0077,0.0071,0.0066,0.0063,0.0064,0.0060,0.0057,0.0055,0.0054,0.0051,0.0047,0.0046,0.0042,0.0037,0.0035,0.0040,0.0043,0.0039,0.0032,0.0028,0.0028,0.0027,0.0029,0.0034,0.0038,0.0034,0.0027,0.0024,0.0021,0.0017,0.0015,0.0016,0.0015,0.0011,0.0008,0.0012,0.0019,0.0025,0.0027,0.0026,0.0019,0.0012,0.0010,0.0014,0.0016,0.0014,0.0010,0.0007,0.0007,0.0010,0.0017,0.0021,0.0020,0.0013,0.0012,0.0013,0.0014,0.0015,0.0018,0.0017,0.0012,0.0013,0.0018,0.0028,0.0031,0.0033,0.0027,0.0022,0.0015,0.0016,0.0022,0.0026,0.0026,0.0019,0.0012,0.0006,0.0007,0.0011,0.0016,0.0014,0.0010,0.0009,0.0012,0.0015,0.0014,0.0008,0.0001,-0.0003,0.0002]
Category = ["a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b"]
df = pd.DataFrame({"Temperature": Temperature,
"Derivative": Derivative,
"Category" : Category})
g = sns.factorplot(x="Temperature", y="Derivative", data=df, col="Category")
g.set_xticklabels(step=10)

All the desired feature you describe suggest that using a factorplot here is absolutely the wrong choice. Instead use a normal matplotlib plot and then set the limits as usual, plt.xlim(60,95).
import pandas as pd
import matplotlib.pyplot as plt
Temperature = [63.0,63.3,63.6,63.9,64.2,64.5,64.8,65.2,65.5,65.8,66.1,66.4,66.7,67.0,67.3,67.7,68.0,68.3,68.6,68.9,69.2,69.5,69.9,70.2,70.5,70.8,71.1,71.4,71.8,72.1,72.4,72.7,73.0,73.4,73.7,74.0,74.3,74.6,74.9,75.2,75.6,75.9,76.2,76.5,76.9,77.2,77.5,77.8,78.1,78.5,78.8,79.1,79.4,79.7,80.1,80.4,80.7,81.0,81.3,81.6,81.9,82.3,82.6,82.9,83.2,83.5,83.8,84.1,84.4,84.8,85.1,85.4,85.7,86.0,86.3,86.6,86.9,87.2,87.5,87.8,88.1,88.4,88.7,89.0,89.3,89.6,89.8,90.1,90.4,90.7,91.0,91.2,91.5,91.8,92.1,63.0,63.3,63.6,63.9,64.2,64.5,64.8,65.2,65.5,65.8,66.1,66.4,66.7,67.0,67.3,67.7,68.0,68.3,68.6,68.9,69.2,69.5,69.9,70.2,70.5,70.8,71.1,71.4,71.8,72.1,72.4,72.7,73.0,73.4,73.7,74.0,74.3,74.6,74.9,75.2,75.6,75.9,76.2,76.5,76.9,77.2,77.5,77.8,78.1,78.5,78.8,79.1,79.4,79.7,80.1,80.4,80.7,81.0,81.3,81.6,81.9,82.3,82.6,82.9,83.2,83.5,83.8,84.1,84.4,84.8,85.1,85.4,85.7,86.0,86.3,86.6,86.9,87.2,87.5,87.8,88.1,88.4,88.7,89.0,89.3,89.6,89.8,90.1,90.4,90.7,91.0,91.2,91.5,91.8,92.1]
Derivative = [0.0495,0.0507,0.0525,0.0548,0.0570,0.0579,0.0579,0.0574,0.0574,0.0576,0.0581,0.0587,0.0593,0.0592,0.0584,0.0580,0.0579,0.0580,0.0582,0.0588,0.0592,0.0594,0.0588,0.0581,0.0578,0.0579,0.0580,0.0579,0.0582,0.0581,0.0579,0.0574,0.0571,0.0563,0.0548,0.0538,0.0536,0.0540,0.0544,0.0551,0.0556,0.0551,0.0542,0.0535,0.0536,0.0542,0.0564,0.0623,0.0748,0.0982,0.1360,0.1897,0.2550,0.3228,0.3807,0.4177,0.4248,0.3966,0.3365,0.2558,0.1713,0.0971,0.0438,0.0140,0.0034,0.0028,0.0048,0.0058,0.0057,0.0050,0.0042,0.0038,0.0039,0.0041,0.0038,0.0031,0.0023,0.0017,0.0014,0.0012,0.0015,0.0019,0.0020,0.0018,0.0017,0.0015,0.0014,0.0014,0.0015,0.0014,0.0013,0.0011,0.0007,0.0004,0.0011,0.0105,0.0100,0.0096,0.0090,0.0084,0.0081,0.0077,0.0071,0.0066,0.0063,0.0064,0.0060,0.0057,0.0055,0.0054,0.0051,0.0047,0.0046,0.0042,0.0037,0.0035,0.0040,0.0043,0.0039,0.0032,0.0028,0.0028,0.0027,0.0029,0.0034,0.0038,0.0034,0.0027,0.0024,0.0021,0.0017,0.0015,0.0016,0.0015,0.0011,0.0008,0.0012,0.0019,0.0025,0.0027,0.0026,0.0019,0.0012,0.0010,0.0014,0.0016,0.0014,0.0010,0.0007,0.0007,0.0010,0.0017,0.0021,0.0020,0.0013,0.0012,0.0013,0.0014,0.0015,0.0018,0.0017,0.0012,0.0013,0.0018,0.0028,0.0031,0.0033,0.0027,0.0022,0.0015,0.0016,0.0022,0.0026,0.0026,0.0019,0.0012,0.0006,0.0007,0.0011,0.0016,0.0014,0.0010,0.0009,0.0012,0.0015,0.0014,0.0008,0.0001,-0.0003,0.0002]
Category = ["a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","a","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b","b"]
df = pd.DataFrame({"Temperature": Temperature,
"Derivative": Derivative,
"Category" : Category})
for n, data in df.groupby("Category"):
plt.plot(data["Temperature"],data["Derivative"] , marker="o", label=n)
plt.xlim(60,95)
plt.legend()
plt.show()
Or if subplots are desired,
fig,axes = plt.subplots(ncols=len(df["Category"].unique()), sharey=True)
for ax,(n, data) in zip(axes,df.groupby("Category")):
ax.plot(data["Temperature"],data["Derivative"] , marker="o", label=n)
ax.set_title("Category {}".format(n))
ax.set_xlim(60,95)
plt.show()
Finally, you may use a seaborn FacetGrid onto which you plot your data with a plot:
g = sns.FacetGrid(df, col="Category")
g.map(plt.plot, "Temperature", "Derivative",marker="o",)
for ax in g.axes.flat:
ax.set_xlim(60,95)
plt.show()

making colorbar values integer in a heatmap matplotlib seaborn

I'm trying to make my colourbar have integer values instead of decimals, but coding this is a lot harder than anticipated.
my initial code
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
#sns.set()
# read data
revels_data = pd.read_csv("revels2.txt")
rd = revels_data
revels = rd.pivot("Flavour", "Packet number", "Contents")
# orders flavours
revels.index = pd.CategoricalIndex(revels.index, categories=["orange", "toffee", "chocolate", "malteser", "raisin", "coffee"])
revels.sortlevel(level=0, inplace=True)
# Draw a heatmap with the numeric values in each cell
ax = sns.heatmap(revels, annot=True, fmt="d", linewidths=0.4, cmap="YlOrRd")
ax.set_title('REVELS PACKET COUNT HEATMAP', weight="bold")
plt.show()
which produces
Trying to reverse engineer one of the answers from here
by adding the following code
cmap = plt.get_cmap("YlOrRd", np.max(rd.Contents)-np.min(rd.Contents)+1)
plt.get_cmap("YlOrRd", np.max(rd.Contents)-np.min(rd.Contents)+1)
# set limits .5 outside true range
mat = plt.matshow(rd.Contents, cmap=cmap, vmin = np.min(rd.Contents)-.5, vmax = np.max(rd.Contents)+.5)
plt.matshow(rd.Contents ,cmap=cmap, vmin = np.min(rd.Contents)-.5, vmax = np.max(rd.Contents)+.5)
#tell the colorbar to tick at integers
cax = plt.colorbar(mat, ticks=np.arange(np.min(rd.Contents),np.max(rd.Contents)+1))
plt.colorbar(mat, ticks=np.arange(np.min(rd.Contents),np.max(rd.Contents)+1))
but getting errors, namely ValueError: not enough values to unpack.
I think I may have applied the code wrong, would appreciate any help.

Here is a full working example, which creates a discrete colorbar for a seaborn heatmap plot with integer values as colorbar ticks.
import pandas as pd
import numpy as np; np.random.seed(8)
import matplotlib.pyplot as plt
import seaborn.apionly as sns
plt.rcParams["figure.figsize"] = 10,5.5
flavours=["orange", "toffee", "chocolate", "malteser", "raisin", "coffee"]
num = np.arange(0, 6*36).astype(int) % 36
flavs = np.random.choice(flavours, size=len(num))
conts = np.random.randint(0,6, len(num)).astype(int)
df = pd.DataFrame({"Packet number":num ,"Flavour":flavs,"Contents" : conts})
revels = pd.pivot_table(df, index=["Flavour"], columns=["Packet number"], values="Contents", aggfunc=np.sum)
revels.index = pd.CategoricalIndex(revels.index, categories=flavours)
revels.sortlevel(level=0, inplace=True)
revels= revels.fillna(0)
ticks=np.arange(revels.values.min(),revels.values.max()+1 )
boundaries = np.arange(revels.values.min()-.5,revels.values.max()+1.5 )
cmap = plt.get_cmap("YlOrRd", revels.values.max()-revels.values.min()+1)
ax = sns.heatmap(revels, annot=True, linewidths=0.4, cmap=cmap,
cbar_kws={"ticks":ticks, "boundaries":boundaries})
ax.set_title('REVELS PACKET COUNT HEATMAP', weight="bold")
plt.tight_layout()
plt.show()

Custom legend for Seaborn regplot (Python 3)

I've been trying to follow this How to make custom legend in matplotlib SO question but I think a few things are getting lost in translation. I used a custom color mapping for the different classes of points in my plot and I want to be able to put a table with those color-label pairs. I stored the info in a dictionary D_color_label and then made 2 parallel lists colors and labels. I tried using it in the ax.legend but it didn't seem to work.
np.random.seed(0)
# Create dataframe
DF_0 = pd.DataFrame(np.random.random((100,2)), columns=["x","y"])
# Label to colors
D_idx_color = {**dict(zip(range(0,25), ["#91FF61"]*25)),
**dict(zip(range(25,50), ["#BA61FF"]*25)),
**dict(zip(range(50,75), ["#916F61"]*25)),
**dict(zip(range(75,100), ["#BAF1FF"]*25))}
D_color_label = {"#91FF61":"label_0",
"#BA61FF":"label_1",
"#916F61":"label_2",
"#BAF1FF":"label_3"}
# Add color column
DF_0["color"] = pd.Series(list(D_idx_color.values()), index=list(D_idx_color.keys()))
# Plot
fig, ax = plt.subplots(figsize=(8,8))
sns.regplot(data=DF_0, x="x", y="y", scatter_kws={"c":DF_0["color"]}, ax=ax)
# Add custom legend
colors = list(set(DF_0["color"]))
labels = [D_color_label[x] for x in set(DF_0["color"])]
# If I do this, I get the following error:
# ax.legend(colors, labels)
# UserWarning: Legend does not support '#BA61FF' instances.
# A proxy artist may be used instead.

According to http://matplotlib.org/users/legend_guide.html you have to put to legend function artists which will be labeled. To use scatter_plot individually you have to group by your data by color and plot every data of one color individually to set its own label for every artist:
import pandas as pd
import numpy as np
import matplotlib.pylab as plt
import seaborn as sns
np.random.seed(0)
# Create dataframe
DF_0 = pd.DataFrame(np.random.random((100, 2)), columns=["x", "y"])
DF_0['color'] = ["#91FF61"]*25 + ["#BA61FF"]*25 + ["#91FF61"]*25 + ["#BA61FF"]*25
#print DF_0
D_color_label = {"#91FF61": "label_0", "#BA61FF": "label_1",
"#916F61": "label_2", "#BAF1FF": "label_3"}
colors = list(DF_0["color"].uniqe())
labels = [D_color_label[x] for x in DF_0["color"].unique()]
ax = sns.regplot(data=DF_0, x="x", y="y", scatter_kws={'c': DF_0['color'], 'zorder':1})
# Make a legend
# groupby and plot points of one color
for i, grp in DF_0.groupby(['color']):
grp.plot(kind='scatter', x='x', y='y', c=i, ax=ax, label=labels[i+1], zorder=0)
ax.legend(loc=2)
plt.show()