Generating Legend for geopandas plot - python

I am plotting a shape file with Geopandas. Additionally im Adding Points of a dataframe (see picture). Now im trying to add a legend (at the right of the original plot) for the point. I dont really know how to do that!
Plot
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import geopandas as gpd
import test
variable = 'RTD_rtd'
df = test.getdataframe()
gdf = gpd.GeoDataFrame(
df, geometry=gpd.points_from_xy(df.NP_LongDegree, df.NP_LatDegree))
fp = "xxx"
map_df = gpd.read_file(fp)
ax = map_df.plot(color='white', edgecolor='black', linewidth=0.4, figsize= (10,10))
gdf.plot(column=variable, ax=ax, cmap='Reds', markersize=14.0, linewidth=2.0)
plt.show()
One Idea was to add a simple legend. I want something looking better. Maybe something similar to whats done in this tutorial: Tutorial

I followed the example that you referred to and this is the concise version. It would have been better if you could have shared a bit of your dataset 'df'. It seems that you want to have a colorbar which fig.colorbar generates.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import geopandas as gpd
import test
from shapely.geometry import Point
df = pd.read_csv('london-borough-profiles.csv', header=0)
df = df[['Area name','Population density (per hectare) 2017']]
fp = 'London_Borough_Excluding_MHW.shp'
map_df = gpd.read_file(fp)
gdf = map_df.set_index('NAME').join(df.set_index('Area name'))
variable = 'Population density (per hectare) 2017'
vmin, vmax = 120, 220
fig, ax = plt.subplots(1, figsize=(10, 6))
gdf.plot(column=variable, cmap='Blues', ax = ax, linewidth=0.8, edgecolor='0.8')
ax.axis('off')
ax.set_title('Population density (per hectare) 2017', fontdict={'fontsize': '25', 'fontweight' : '3'})
ax.annotate('Source: London Datastore, 2014',xy=(0.1, .08), xycoords='figure fraction', horizontalalignment='left', verticalalignment='top', fontsize=12, color='#555555')
sm = plt.cm.ScalarMappable(cmap='Blues', norm=plt.Normalize(vmin=vmin, vmax=vmax))
sm._A = []
cbar = fig.colorbar(sm)

You can add this into your solution and for this you have to set label for each plot
plt.legend()

Related

matplotlib - dataframe - How to have real map on the background in matplotlib

The codes below put dots on the specific points on the earth map.
num_samples = 1250000
indices = np.random.choice(df.index, num_samples)
df_x = df.df_longitude[indices].values
df_y = df.df_latitude[indices].values
sns.set_style('white')
fig, ax = plt.subplots(figsize=(11, 12))
ax.scatter(df_x, df_y, s=5, color='red', alpha=0.5)
ax.set_xlim([-74.10, -73.60])
ax.set_ylim([40.85, 40.90])
ax.set_title('coordinates')
Is there any way to put these dots on a map instead of this white background?
Please have a look at the picture below:
geopandas provides an API that makes this quite easy. Here is an example, where the map is zoom into the continent of Africa:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import geopandas
df = pd.DataFrame(
{'Latitude': np.random.uniform(-20,10, 100),
'Longitude': np.random.uniform(40,20, 100)})
gdf = geopandas.GeoDataFrame(
df, geometry=geopandas.points_from_xy(df.Longitude, df.Latitude))
world = geopandas.read_file(geopandas.datasets.get_path('naturalearth_lowres'))
ax = world[world.continent == 'Africa'].plot(color='white', edgecolor='black')
# We can now plot our ``GeoDataFrame``.
gdf.plot(ax=ax, color='red')
plt.show()
The result:

Add different shade colors for trend and forecast , with text on the region

import numpy as np
import pandas as pd
df = pd.DataFrame({"y" : np.random.rand(20)})
ax = df.iloc[:15,:].plot(ls="-", color="b")
ax2 = ax.twinx() #Create a twin Axes sharing the xaxis
df.iloc[15:,:].plot(ls="--", color="r", ax=ax)
plt.axhline(y=0.5,linestyle="--",animated=True,label="False Alaram")
plt.show()
So, first 15 are trend and last 5 are predictions.
I want different colors for trend and pred in background.
Also, how can i add text "Historic" and "Forecast" on graph.
I believe you're looking for fill_between:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
df = pd.DataFrame({"y" : np.random.rand(20)})
fig, ax = plt.subplots(figsize=(8,6))
df.iloc[:15,:].plot(ls="-", color="b", ax=ax)
plt.fill_between(df.iloc[:15].index.tolist(), df.iloc[:15].y.tolist(), alpha=.25, color='b')
df.iloc[15:,:].plot(ls="--", color="r", ax=ax)
plt.axhline(y=0.5,linestyle="--", animated=True, label="False Alaram")
plt.fill_between(df.iloc[15:].index.tolist(), df.iloc[15:].y.tolist(), alpha=.25, color='r')
plt.legend()
plt.show()

Geopandas with log-scale colormap

If I have the plot below, how can I turn the colormap/legend into a log-scale?
import geopandas as gpd
import matplotlib.pyplot as plt
world = gpd.read_file(gpd.datasets.get_path('naturalearth_lowres'))
world = world[(world.pop_est>0) & (world.name!="Antarctica")]
fig, ax = plt.subplots(1, 1)
world.plot(column='pop_est', ax=ax, legend=True)
GeoPandas plots are using matplotlib, so you can use normalization of colormap provided by it. Note than I am also specifying min and max values as mins and maxs of the column I am plotting.
world.plot(column='pop_est', legend=True, norm=matplotlib.colors.LogNorm(vmin=world.pop_est.min(), vmax=world.pop_est.max()), )
You can simply plot the log of the value instead of the value itself.
import geopandas as gpd
import matplotlib.pyplot as plt
from numpy import log10
world = gpd.read_file(gpd.datasets.get_path('naturalearth_lowres'))
world = world[(world.pop_est>0) & (world.name!="Antarctica")]
world['logval'] = log10(world['pop_est'])
fig, ax = plt.subplots(1, 1)
world.plot(column='logval', ax=ax, legend=True)

Highlighting maximum value in a column on a seaborn heatmap

I have a seaborn.heatmap plotted from a DataFrame:
import seaborn as sns
import matplotlib.pyplot as plt
fig = plt.figure(facecolor='w', edgecolor='k')
sns.heatmap(collected_data_frame, annot=True, vmax=1.0, cmap='Blues', cbar=False, fmt='.4g')
I would like to create some sort of highlight for a maximum value in each column - it could be a red box around that value, or a red dot plotted next to that value, or the cell could be colored red instead of using Blues. Ideally I'm expecting something like this:
I got the highlight working for DataFrame printing in Jupyter Notebook using tips from this answer:
How can I achieve a similar thing but on a heatmap?
We've customized the heatmap examples in the official reference. The customization examples were created from the responses from this site. It's a form of adding parts to an existing graph. I added a frame around the maximum value, but this is manual.
import matplotlib.pyplot as plt
from matplotlib.patches import Rectangle
import seaborn as sns
sns.set()
# Load the example flights dataset and convert to long-form
flights_long = sns.load_dataset("flights")
flights = flights_long.pivot("month", "year", "passengers")
# Draw a heatmap with the numeric values in each cell
f, ax = plt.subplots(figsize=(9, 6))
ax = sns.heatmap(flights, annot=True, fmt="d", linewidths=.5, ax=ax)
ax.add_patch(Rectangle((10,6),2,2, fill=False, edgecolor='blue', lw=3))
max value:
ymax = max(flights)
ymax
1960
flights.columns.get_loc(ymax)
11
xmax = flights[ymax].idxmax()
xmax
'July'
xpos = flights.index.get_loc(xmax)
xpos
6
ax.add_patch(Rectangle((ymax,xpos),1,1, fill=False, edgecolor='blue', lw=3))
Complete solution based on the answer of #r-beginners:
Generate DataFrame:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.patches import Rectangle
import seaborn
arr = np.array([[0.9336719 , 0.90119269, 0.90791181, 0.3112451 , 0.56715989,
0.83339874, 0.14571595, 0.36505745, 0.89847367, 0.95317909,
0.16396293, 0.63463356],
[0.93282304, 0.90605976, 0.91276066, 0.30288519, 0.56366228,
0.83032344, 0.14633036, 0.36081791, 0.9041638 , 0.95268572,
0.16803188, 0.63459491],
[0.15215358, 0.4311569 , 0.32324376, 0.51620611, 0.69872915,
0.08811177, 0.80087247, 0.234593 , 0.47973905, 0.21688613,
0.2738223 , 0.38322856],
[0.90406056, 0.89632902, 0.92220635, 0.3022458 , 0.58843012,
0.78159595, 0.17089609, 0.33443782, 0.89997103, 0.93128579,
0.15942313, 0.62644379],
[0.93868063, 0.45617598, 0.17708323, 0.81828266, 0.72986428,
0.82543775, 0.41530088, 0.2604382 , 0.33132295, 0.94686745,
0.05607774, 0.54141198]])
columns_text = [str(num) for num in range(0,12)]
index_text = ['C1', 'C2', 'C3', 'C4', 'C5']
arr_data_frame = pd.DataFrame(arr, columns=columns_text, index=index_text)
Highlighting maximum in a column:
fig,ax = plt.subplots(figsize=(15, 3), facecolor='w', edgecolor='k')
ax = seaborn.heatmap(arr_data_frame, annot=True, vmax=1.0, vmin=0, cmap='Blues', cbar=False, fmt='.4g', ax=ax)
column_max = arr_data_frame.idxmax(axis=0)
for col, variable in enumerate(columns_text):
position = arr_data_frame.index.get_loc(column_max[variable])
ax.add_patch(Rectangle((col, position),1,1, fill=False, edgecolor='red', lw=3))
plt.savefig('max_column_heatmap.png', dpi = 500, bbox_inches='tight')
Highlighting maximum in a row:
fig,ax = plt.subplots(figsize=(15, 3), facecolor='w', edgecolor='k')
ax = seaborn.heatmap(arr_data_frame, annot=True, vmax=1.0, vmin=0, cmap='Blues', cbar=False, fmt='.4g', ax=ax)
row_max = arr_data_frame.idxmax(axis=1)
for row, index in enumerate(index_text):
position = arr_data_frame.columns.get_loc(row_max[index])
ax.add_patch(Rectangle((position, row),1,1, fill=False, edgecolor='red', lw=3))
plt.savefig('max_row_heatmap.png', dpi = 500, bbox_inches='tight')

How to use pandas df.plot.scatter to make a figure with subplots

Hello how can i make a figure with scatter subplots using pandas? Its working with plot, but not with scatter.
Here an Example
import numpy as np
import pandas as pd
matrix = np.random.rand(200,5)
df = pd.DataFrame(matrix,columns=['index','A','B','C','D'])
#single plot, working with
df.plot(
kind='scatter',
x='index',
y='A',
s= 0.5
)
# not workig
df.plot(
subplots=True,
kind='scatter',
x='index',
y=['A','B','C'],
s= 0.5
)
Error
raise ValueError(self._kind + " requires an x and y column")
ValueError: scatter requires an x and y column
Edit:
Solution to make a figure with subplots with using df.plot
(Thanks to #Fourier)
import numpy as np
import pandas as pd
matrix = np.random.rand(200,5)#random data
df = pd.DataFrame(matrix,columns=['index','A','B','C','D']) #make df
#get a list for subplots
labels = list(df.columns)
labels.remove('index')
df.plot(
layout=(-1, 5),
kind="line",
x='index',
y=labels,
subplots = True,
sharex = True,
ls="none",
marker="o")
Would this work for you:
import pandas as pd
import numpy as np
df = pd.DataFrame({"index":np.arange(5),"A":np.random.rand(5),"B":np.random.rand(5),"C":np.random.rand(5)})
df.plot(kind="line", x="index", y=["A","B","C"], subplots=True, sharex=True, ls="none", marker="o")
Output
Note: This uses a line plot with invisible lines. For a scatter, I would go and loop over it.
for column in df.columns[:-1]: #[:-1] ignores the index column for my random sample
df.plot(kind="scatter", x="index", y=column)
EDIT
In order to add custom ylabels you can do the following:
axes = df.plot(kind='line', x="index", y=["A","B","C"], subplots=True, sharex=True, ls="none", marker="o", legend=False)
ylabels = ["foo","bar","baz"]
for ax, label in zip(axes, ylabels):
ax.set_ylabel(label)

Categories

Resources