We Keep Coding

Can't plot comparative (double) histogram from Pandas table

Here's the table from the dataframe:
Points_groups
Qty Contracts
Qty Gones
1
350+
108
275
2
300-350
725
1718
3
250-300
885
3170
4
200-250
2121
10890
5
150-200
3120
7925
6
100-150
653
1318
7
50-100
101
247
8
0-50
45
137
I'd like to get something like this out of it:
But that the columns correspond to the 'x' axis,
which was built from the 'Scores_groups' column like this
I tried a bunch of options already, but I couldn't get it.
For example:
df.plot(kind ='hist')
plt.xlabel('Points_groups')
plt.ylabel("Number Of Students");
or
sns.distplot(df['Кол-во Ушедшие'])
sns.distplot(df['Кол-во Контракт'])
plt.show()
or
df.hist(column='Баллы_groups', by= ['Кол-во Контракт', 'Кол-во Ушедшие'], bins=2, grid=False, rwidth=0.9,color='purple', sharex=True);

Since you already have the distribution in your pandas dataframe, the plot you need can be achieved with the following code:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
Df = pd.DataFrame({'key': ['red', 'green', 'blue'], 'A': [1, 2, 1], 'B': [2, 4, 3]})
X_axis = np.arange(len(Df['key']))
plt.bar(X_axis - 0.2, Df['A'], 0.4, label = 'A')
plt.bar(X_axis + 0.2, Df['B'], 0.4, label = 'B')
X_label = list(Df['key'].values)
plt.xticks(X_axis, X_label)
plt.legend()
plt.show()
Since I don't have access to your data, I made some mock dataframe. This results in the following figure:

Spatial pie chart using geopandas

I am trying to make a pie chart that looks like the below -
I am using geopandas for that-
us_states = gpd.read_file("conus_state.shp")
data = gpd.read_file("data_file.shp")
fig, ax = plt.subplots(figsize= (10,10))
us_states.plot(color = "None", ax = ax)
data.plot(column = ["Column1","Column2"], ax= ax, kind = "pie",subplots=True)
This gives me the following error-
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
C:\Users\LSRATH~1.STU\AppData\Local\Temp/ipykernel_17992/1047905594.py in <module>
1 fig, ax = plt.subplots(figsize= (10,10))
2 us_states.plot(color = "None", ax = ax)
----> 3 diff_env.plot(column = ["WS_MON1","WS_MON2"], ax= ax, kind = "pie")
c:\python38\lib\site-packages\geopandas\plotting.py in __call__(self, *args, **kwargs)
951 if kind in self._pandas_kinds:
952 # Access pandas plots
--> 953 return PlotAccessor(data)(kind=kind, **kwargs)
954 else:
955 # raise error
c:\python38\lib\site-packages\pandas\plotting\_core.py in __call__(self, *args, **kwargs)
921 if isinstance(data, ABCDataFrame):
922 if y is None and kwargs.get("subplots") is False:
--> 923 raise ValueError(
924 f"{kind} requires either y column or 'subplots=True'"
925 )
ValueError: pie requires either y column or 'subplots=True'
Even after specifying, subplots = True, it does not work.
How can I make a pie chart using 2 columns of the dataframe?
Below are the first five rows of the relevant columns-
diff_env[["Column1", "Column2", "geometry"]].head().to_dict()
{'Column1': {0: 2, 1: 0, 2: 0, 3: 1, 4: 12},
'Column2': {0: 2, 1: 0, 2: 0, 3: 1, 4: 12},
'geometry': {0: <shapely.geometry.point.Point at 0x2c94e07f190>,
1: <shapely.geometry.point.Point at 0x2c94e07f130>,
2: <shapely.geometry.point.Point at 0x2c94e07f0d0>,
3: <shapely.geometry.point.Point at 0x2c94bb86d30>,
4: <shapely.geometry.point.Point at 0x2c94e07f310>}}

you have not provided any usable sample data. Have randomly generated some
this is inspired by How to plot scatter pie chart using matplotlib
sample data
value0
value1
geometry
size
0
5
3
POINT (-105.96116535117056 31.014979334448164)
312
1
2
3
POINT (-79.70609244147155 36.46222924414716)
439
2
4
7
POINT (-68.89518006688962 37.84436728093645)
363
3
7
9
POINT (-118.12344177257525 31.909303946488293)
303
4
2
7
POINT (-102.1001252173913 28.57591221070234)
326
5
3
3
POINT (-96.88772103678929 47.76324025083612)
522
6
5
8
POINT (-112.33188157190635 48.16975143812709)
487
7
7
6
POINT (-95.15025297658862 44.59245298996656)
594
8
3
1
POINT (-100.36265715719063 46.787613401337794)
421
9
2
4
POINT (-81.82966451505015 35.161393444816056)
401
full code
import geopandas as gpd
import numpy as np
import shapely
import matplotlib.pyplot as plt
states = (
gpd.read_file(
"https://raw.githubusercontent.com/nvkelso/natural-earth-vector/master/geojson/ne_110m_admin_1_states_provinces.geojson"
)
.loc[lambda d: d["iso_3166_2"].ne("US-AK"), "geometry"]
.exterior
)
# geodataframe of points where pies are to be plotted
n = 10
pies = gpd.GeoDataFrame(
geometry=[
shapely.geometry.Point(xy)
for xy in zip(
np.random.choice(np.linspace(*states.total_bounds[[0, 2]], 300), n),
np.random.choice(np.linspace(*states.total_bounds[[1, 3]], 300), n),
)
],
data={f"value{c}": np.random.randint(1, 10, n) for c in range(2)},
crs=states.crs,
).pipe(lambda d: d.assign(size=np.random.randint(300, 600, n)))
# utility function inspired by https://stackoverflow.com/questions/56337732/how-to-plot-scatter-pie-chart-using-matplotlib
def draw_pie(dist, xpos, ypos, size, ax):
# for incremental pie slices
cumsum = np.cumsum(dist)
cumsum = cumsum / cumsum[-1]
pie = [0] + cumsum.tolist()
colors = ["blue", "red", "yellow"]
for i, (r1, r2) in enumerate(zip(pie[:-1], pie[1:])):
angles = np.linspace(2 * np.pi * r1, 2 * np.pi * r2)
x = [0] + np.cos(angles).tolist()
y = [0] + np.sin(angles).tolist()
xy = np.column_stack([x, y])
ax.scatter([xpos], [ypos], marker=xy, s=size, color=colors[i], alpha=1)
return ax
fig, ax = plt.subplots()
ax = states.plot(ax=ax, edgecolor="black", linewidth=0.5)
for _, r in pies.iterrows():
ax = draw_pie([r.value0, r.value1], r.geometry.x, r.geometry.y, r["size"], ax)
output

No numeric types to aggregate error while plotting bar graph in matplotlib

I got a 'No numeric types to aggregate' error when I run the following code.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
x_labels = ['Female', 'Male']
genderincomeTM1 = round(TM1.groupby('Gender')['Income'].mean())
genderincomeTM2 = round(TM2.groupby('Gender')['Income'].mean())
genderincomeTM3 = round(TM3.groupby('Gender')['Income'].mean())
genderTM1 = genderincomeTM1.index
genderTM2 = genderincomeTM2.index
genderTM3 = genderincomeTM3.index
x = np.arange(len(x_labels))
plt.figure(figsize=(12,8))
width = 0.35
fig, ax = plt.subplots()
bar1 = ax.bar(x - 0.3, genderincomeTM1, width=0.2, label='TM1')
bar2 = ax.bar(x, genderincomeTM2, width=0.2, label='TM2')
bar3 = ax.bar(x + 0.3, genderincomeTM3, width=0.2, label='TM3')
ax.set_title('Average Income by Product Model', fontsize = 18)
ax.set_ylabel('Sales', fontsize = 12)
ax.set_xticks(x)
ax.set_xticklabels(x_labels)
ax.set_ylim(bottom = 0, top = 90000)
ax.legend(loc=(1.02,0.4), borderaxespad=0, fontsize = 12)
def autolabel(bars):
for each in bars:
height = each.get_height()
ax.annotate('{}'.format(height),
xy=(each.get_x() + each.get_width() / 2, height),
xytext=(0, 2), # 2 points vertical offset
textcoords="offset points",
ha='center', va='bottom')
autolabel(bar1)
autolabel(bar2)
autolabel(bar3)
DataError Traceback (most recent call last)
<ipython-input-24-fb1aa4ae1242> in <module>
1 x_labels = ['Female', 'Male']
2
----> 3 genderincomeTM1 = round(TM1.groupby('Gender')['Income'].mean())
4 genderincomeTM2 = round(TM2.groupby('Gender')['Income'].mean())
5 genderincomeTM3 = round(TM3.groupby('Gender')['Income'].mean())
~\anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in mean(self, *args, **kwargs)
1223 """
1224 nv.validate_groupby_func("mean", args, kwargs, ["numeric_only"])
-> 1225 return self._cython_agg_general(
1226 "mean", alt=lambda x, axis: Series(x).mean(**kwargs), **kwargs
1227 )
~\anaconda3\lib\site-packages\pandas\core\groupby\groupby.py in _cython_agg_general(self, how, alt, numeric_only, min_count)
906
907 if len(output) == 0:
--> 908 raise DataError("No numeric types to aggregate")
909
910 return self._wrap_aggregated_output(output)
DataError: No numeric types to aggregate
I have removed all empty rows and checked on 'Income' column using is_numeric_dtype. I also converted the column to int.
from pandas.api.types import is_numeric_dtype
is_numeric_dtype(df['Income'])
>True
df['Income'] = df['Income'].astype(int)
df.info()
><class 'pandas.core.frame.DataFrame'>
>Int64Index: 180 entries, 0 to 182
>Data columns (total 10 columns):
> # Column Non-Null Count Dtype
>--- ------ -------------- -----
> 0 Product 180 non-null object
> 1 Branch 180 non-null object
> 2 Age 180 non-null object
> 3 Gender 180 non-null object
> 4 Education 180 non-null object
> 5 MaritalStatus 180 non-null object
> 6 Usage 180 non-null object
> 7 Fitness 180 non-null object
> 8 Income 180 non-null int32
I am confused why there is no numeric type for Income after validation. Could it be referring to 'Gender'? How should I go about resolving the error?

I can't probably answer your question, because you haven't provided a dataframe which reproduces the error. Maybe you could start by running this code:
import numpy as np
import pandas as pd
TM1 = pd.DataFrame({'Gender':['M','F','M','F'],'Income':['10','20','30','40']})
TM1['Income'] = TM1.Income.astype(int)
TM1.groupby('Gender')['Income'].mean().round()
Because the incomes are initially given as strings, the mean can't be computed until they're converted to integers.

number of observation on violinplot is not good

I use this tips https://python-graph-gallery.com/58-show-number-of-observation-on-violinplot/ to add Number of observation on a violon plot.
Here is m code:
# Calculate number of obs per group & median to position labels
medians = dataset.groupby([x_attrib])[y_attrib].median().values
nobs = dataset[x_attrib].value_counts().values
nobs = [str(x) for x in nobs.tolist()]
#nobs = ["Nb: " + i for i in nobs]
nobs = [i for i in nobs]
# Add it to the plot
pos = range(len(nobs))
for tick,label in zip(pos,ax.get_xticklabels()):
ax.text(pos[tick], medians[tick] + 0.03, nobs[tick], horizontalalignment='center', size='x-large', color='black', weight='semibold')
I plot variable with these value counts:
0 355
1 174
2 36
-1 19
3 15
4 5
...
As you can see on the plot, for -1 value: real count is 19 and the plot return 355 (count for 0 value)
How can i modify the code to get a good plot please?
Thanks a lot.
Theo

compute the difference of all possible rows

Based on a selection ds of a dataframe d with:
{ 'x': d.x, 'y': d.y, 'a':d.a, 'b':d.b, 'c':d.c 'row:d.n'})
Having n rows, x ranges from 0 to n-1. The column n is needed since it's a selection and indices need to be kept for a later query.
How do you efficiently compute the difference between each row (e.g.a_0, a_1, etc) of each column (a, b, c) without losing the rows information (e.g. new column with the indices of the rows that were used) ?
MWE
Sample selection ds:
x y a b c n
554.607085 400.971878 9789 4151 6837 146
512.231450 405.469524 8796 3811 6596 225
570.427284 694.369140 1608 2019 2097 291
Desired output:
dist euclidean distance math.hypot(x2 - x1, y2 - y1)
da, db, dc for da: np.abs(a1-a2)
ns a string with both ns of the employed rows
the result would look like:
dist da db dc ns
42.61365102824963 993 340 241 146-225
293.82347069813255 8181 2132 4740 146-291
.. .. .. .. 225-291

You can use itertools.combinations() to generate the pairs:
Read data first:
import pandas as pd
from io import StringIO
import numpy as np
text = """ x y a b c n
554.607085 400.971878 9789 4151 6837 146
512.231450 405.469524 8796 3811 6596 225
570.427284 694.369140 1608 2019 2097 291"""
df = pd.read_csv(StringIO(text), delim_whitespace=True)
Create the index and calculate the results:
from itertools import combinations
index = np.array(list(combinations(range(df.shape[0]), 2)))
df1, df2 = [df.iloc[idx].reset_index(drop=True) for idx in index.T]
res = pd.concat([
np.hypot(df1.x - df2.x, df1.y - df2.y),
df1[["a", "b", "c"]] - df2[["a", "b", "c"]],
df1.n.astype(str) + "-" + df2.n.astype(str)
], axis=1)
res.columns = ["dist", "da", "db", "dc", "ns"]
res
the output:
dist da db dc ns
0 42.613651 993 340 241 146-225
1 293.823471 8181 2132 4740 146-291
2 294.702805 7188 1792 4499 225-291

This approach makes good use of Pandas and the underlying numpy capabilities, but the matrix manipulations are a little hard to keep track of:
import pandas as pd, numpy as np
ds = pd.DataFrame(
[
[554.607085, 400.971878, 9789, 4151, 6837, 146],
[512.231450, 405.469524, 8796, 3811, 6596, 225],
[570.427284, 694.369140, 1608, 2019, 2097, 291]
],
columns = ['x', 'y', 'a', 'b', 'c', 'n']
)
def concat_str(*arrays):
result = arrays[0]
for arr in arrays[1:]:
result = np.core.defchararray.add(result, arr)
return result
# Make a panel with one item for each column, with a square data frame for
# each item, showing the differences between all row pairs.
# This creates perpendicular matrices of values based on the underlying numpy arrays;
# then numpy broadcasts them along the missing axis when calculating the differences
p = pd.Panel(
(ds.values[np.newaxis,:,:] - ds.values[:,np.newaxis,:]).transpose(),
items=['d'+c for c in ds.columns], major_axis=ds.index, minor_axis=ds.index
)
# calculate euclidian distance
p['dist'] = np.hypot(p['dx'], p['dy'])
# create strings showing row relationships
p['ns'] = concat_str(ds['n'].values.astype(str)[:,np.newaxis], '-', ds['n'].values.astype(str)[np.newaxis,:])
# remove unneeded items
del p['dx'], p['dy'], p['dn']
# convert to frame
diffs = p.to_frame().reindex_axis(['dist', 'da', 'db', 'dc', 'ns'], axis=1)
diffs
This gives:
dist da db dc ns
major minor
0 0 0.000000 0 0 0 146-146
1 42.613651 993 340 241 146-225
2 293.823471 8181 2132 4740 146-291
1 0 42.613651 -993 -340 -241 225-146
1 0.000000 0 0 0 225-225
2 294.702805 7188 1792 4499 225-291
2 0 293.823471 -8181 -2132 -4740 291-146
1 294.702805 -7188 -1792 -4499 291-225
2 0.000000 0 0 0 291-291