I have a plot made up of 3 choropleth subplots next to each other. I set the overall height and width to my desired dimensions (800 x 400 pixels). I want each subplot to go from top to bottom, but as it stands, the subplots retain the aspect ratio of 2:1, meaning I have wide margins at top and bottom. Those I want to remove.
As a minimum example, I am attaching the data and plot code:
The toy dataset:
import geopandas as gpd
from shapely.geometry.polygon import Polygon
minidf = gpd.GeoDataFrame(dict(
krs_code = ["08111", "08118"],
m_rugged = [42.795776, 37.324421],
bip = [83747, 43122],
cm3_over_1999 = [47.454688, 47.545940],
geometry = [Polygon(((9.0397, 48.6873),
(9.0397, 48.8557),
(9.3152, 48.8557),
(9.3152, 48.6873),
(9.0397, 48.6873))),
Polygon(((8.8757, 48.7536),
(8.8757, 49.0643),
(9.4167, 49.0643),
(9.4167, 48.7536),
(8.8757, 48.7536)))]
)).set_index("krs_code")
The plotting code:
import json
from plotly.subplots import make_subplots
import plotly.graph_objects as go
fig = make_subplots(rows = 1, cols = 3,
specs = [[{"type": "choropleth"}, {"type": "choropleth"}, {"type": "choropleth"}]],
horizontal_spacing = 0.0025 )
fig.update_layout(height = 400, width = 800,
margin = dict(t=0, r=0, b=0, l=0),
coloraxis_showscale=False )
for i, column in enumerate(["m_rugged", "cm3_over_1999", "bip"]):
fig.add_trace(
go.Choropleth(
locations = minidf.index,
z = minidf[column].astype(float), # Data to be color-coded
geojson = json.loads(minidf[["geometry"]].to_json()),
showscale = False
),
col = i+1, row = 1)
fig.update_geos(fitbounds="locations", visible=True)
fig.show()
Notice the margins at top and bottom, which retain the aspect ratio of each subplot, while they are supposed to stretch from top to bottom:
I tried several parameters within go.Choropleth() and .update_layout(), but to no avail.
Related
I am trying to build a graph where the line graph should show the value of only the last element in some beautiful formating.
line graph with no text at end
Now the current method of the text shows for all elements and is a straight text that creates a lot of collisions with different lines in the same graph and looks clumsy.
Will be very nice to achieve something as mentioned in the below image.
desired line graph with text
This is now handled through:
legendgroup = d.name
Plot 1: All
Plot 2: Deselect GOOG in the legend and see that the marker disappears as well:
Complet code:
# imports
import pandas as pd
import plotly.express as px
# data
df = px.data.stocks()
df = df.drop('AMZN', axis = 1)
colors = px.colors.qualitative.T10
# plotly
fig = px.line(df,
x = 'date',
y = [c for c in df.columns if c != 'date'],
template = 'plotly_dark',
color_discrete_sequence = colors,
title = 'Stocks',
)
# move legend
fig.layout.legend.x = -0.3
# add traces for annotations and text for end of lines
for i, d in enumerate(fig.data):
fig.add_scatter(x=[d.x[-1]], y = [d.y[-1]],
mode = 'markers+text',
text = d.y[-1],
textfont = dict(color=d.line.color),
textposition='middle right',
marker = dict(color = d.line.color, size = 12),
legendgroup = d.name,
showlegend=False)
fig.show()
Similar to many other researchers on stackoverflow who are trying to plot a contour graph out of 4D data (i.e., X,Y,Z and their corresponding value C), I am attempting to plot a 4D contour map out of my data. I have tried many of the suggested solutions in stackover flow. From all of the plots suggested this, and this were the closest to what I want but sill not quite what I need in terms of data interpretation. Here is the ideal plot example: (source)
Here is a subset of the data. I put it on the dropbox. Once this data is downloaded to the directory of the python file, the following code will work. I have modified this script from this post.
import numpy as np
from mpl_toolkits.mplot3d import Axes3D
import matplotlib.pyplot as plt
import matplotlib.tri as mtri
#####Importing the data
df = pd.read_csv('Data_4D_plot.csv')
do_random_pt_example = False;
index_x = 0; index_y = 1; index_z = 2; index_c = 3;
list_name_variables = ['x', 'y', 'z', 'c'];
name_color_map = 'seismic';
if do_random_pt_example:
number_of_points = 200;
x = np.random.rand(number_of_points);
y = np.random.rand(number_of_points);
z = np.random.rand(number_of_points);
c = np.random.rand(number_of_points);
else:
x = df['X'].to_numpy();
y = df['Y'].to_numpy();
z = df['Z'].to_numpy();
c = df['C'].to_numpy();
#end
#-----
# We create triangles that join 3 pt at a time and where their colors will be
# determined by the values of their 4th dimension. Each triangle contains 3
# indexes corresponding to the line number of the points to be grouped.
# Therefore, different methods can be used to define the value that
# will represent the 3 grouped points and I put some examples.
triangles = mtri.Triangulation(x, y).triangles;
choice_calcuation_colors = 2;
if choice_calcuation_colors == 1: # Mean of the "c" values of the 3 pt of the triangle
colors = np.mean( [c[triangles[:,0]], c[triangles[:,1]], c[triangles[:,2]]], axis = 0);
elif choice_calcuation_colors == 2: # Mediane of the "c" values of the 3 pt of the triangle
colors = np.median( [c[triangles[:,0]], c[triangles[:,1]], c[triangles[:,2]]], axis = 0);
elif choice_calcuation_colors == 3: # Max of the "c" values of the 3 pt of the triangle
colors = np.max( [c[triangles[:,0]], c[triangles[:,1]], c[triangles[:,2]]], axis = 0);
#end
#----------
###=====adjust this part for the labeling of the graph
list_name_variables[index_x] = 'X (m)'
list_name_variables[index_y] = 'Y (m)'
list_name_variables[index_z] = 'Z (m)'
list_name_variables[index_c] = 'C values'
# Displays the 4D graphic.
fig = plt.figure(figsize = (15,15));
ax = fig.gca(projection='3d');
triang = mtri.Triangulation(x, y, triangles);
surf = ax.plot_trisurf(triang, z, cmap = name_color_map, shade=False, linewidth=0.2);
surf.set_array(colors); surf.autoscale();
#Add a color bar with a title to explain which variable is represented by the color.
cbar = fig.colorbar(surf, shrink=0.5, aspect=5);
cbar.ax.get_yaxis().labelpad = 15; cbar.ax.set_ylabel(list_name_variables[index_c], rotation = 270);
# Add titles to the axes and a title in the figure.
ax.set_xlabel(list_name_variables[index_x]); ax.set_ylabel(list_name_variables[index_y]);
ax.set_zlabel(list_name_variables[index_z]);
ax.view_init(elev=15., azim=45)
plt.show()
Here would be the output:
Although it looks brilliant, it is not quite what I am looking for (the above contour map example). I have modified the following script from this post in the hope to reach the required graph, however, the chart looks nothing similar to what I was expecting (something similar to the previous output graph). Warning: the following code may take some time to run.
import matplotlib
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import numpy as np
df = pd.read_csv('Data_4D_plot.csv')
x = df['X'].to_numpy();
y = df['Y'].to_numpy();
z = df['Z'].to_numpy();
cc = df['C'].to_numpy();
# convert to 2d matrices
Z = np.outer(z.T, z)
X, Y = np.meshgrid(x, y)
C = np.outer(cc.T,cc)
# fourth dimention - colormap
# create colormap according to cc-value
color_dimension = C # change to desired fourth dimension
minn, maxx = color_dimension.min(), color_dimension.max()
norm = matplotlib.colors.Normalize(minn, maxx)
m = plt.cm.ScalarMappable(norm=norm, cmap='jet')
m.set_array([])
fcolors = m.to_rgba(color_dimension)
# plot
fig = plt.figure()
ax = fig.gca(projection='3d')
ax.plot_surface(X,Y,Z, rstride=1, cstride=1, facecolors=fcolors, vmin=minn, vmax=maxx, shade=False)
ax.set_xlabel('x')
ax.set_ylabel('y')
ax.set_zlabel('z')
plt.show()
Now I was wondering from our kind community and experts if you can help me to plot a contour figure similar to the example graph (image one in this post), where the contours are based on the values within the range of C?
I plotted some data which has 70 classes, so when I built the color bar it's very difficult to distinguish between each legend as shown below:
The code that I'm using is:
formation_colors = # 70 colors
formation_labels = # 70 labels
data = # the section of the entire dataset which only has 13 labels
data = data.sort_values(by='DEPTH_MD')
ztop=data.DEPTH_MD.min(); zbot=data.DEPTH_MD.max()
cmap_formations = colors.ListedColormap(formation_colors[0:len(formation_colors)], 'indexed')
cluster_f = np.repeat(np.expand_dims(data['Formations'].values,1), 100, 1)
fig = plt.figure(figsize=(2,10))
ax = fig.add_subplot()
im_f = ax.imshow(cluster_f, interpolation='none', aspect='auto', cmap = cmap_formations, vmin=0, vmax=69)
ax.set_xlabel('FORMATION')
ax.set_xticklabels(['']);
divider_f = make_axes_locatable(ax)
cax_f = divider_f.append_axes("right", size="20%", pad=0.05)
cbar_f = plt.colorbar(im_f, cax = cax_f,)
cbar_f.set_ticks(range(0,len(formation_labels))); cbar_f.set_ticklabels(formation_labels)
So far, if I just change:
1. cmap_formations = colors.ListedColormap(formation_colors[0:len(formation_colors)], 'indexed')
2. cbar_f.set_ticks(range(0,len(formation_labels))); cbar_f.set_ticklabels(formation_labels)
to:
cmap_formations = colors.ListedColormap(formation_colors[0:len(data['FORMATION'].unique())], 'indexed')
cbar_f.set_ticks(range(0,len(data['FORMATION'].unique()))); cbar_f.set_ticklabels(data['FORMATION'].unique())
I get, the corresponding colors in the cbar, however the plot is no longer correct and also the legends are out of square
Thank you so much if you have any idea how to do this.
Although not explicitly mentioned in the question, I suppose data['FORMATION'] contains indices from 0 till 69 into the lists of formation_colors and formation_labels
The main problem is that data['FORMATION'] needs to be renumbered to be new indices (with numbers 0 till 12) into the new list of unique colors. np.unique(..., return_inverse=True) returns both the list of unique numbers, and the renumbering for the values.
To be able to reindex the list of colors and of labels, it helps to convert them to numpy arrays.
To make the code easier to debug, the following test uses a simple relation between the list of colors and the list of labels.
from matplotlib import pyplot as plt
from matplotlib import colors
from mpl_toolkits.axes_grid1.axes_divider import make_axes_locatable
import numpy as np
import pandas as pd
formation_colors = np.random.choice(list(colors.CSS4_COLORS), 70, replace=False) # 70 random color names
formation_labels = ['lbl_' + c for c in formation_colors] # 70 labels
formation_colors = np.asarray(formation_colors)
formation_labels = np.asarray(formation_labels)
f = np.random.randint(0, 70, 13)
d = np.sort(np.random.randint(0, 5300, 13))
data = pd.DataFrame({'FORMATION': np.repeat(f, np.diff(np.append(0, d))),
'DEPTH_MD': np.arange(d[-1])})
data = data.sort_values(by='DEPTH_MD')
ztop = data['DEPTH_MD'].min()
zbot = data['DEPTH_MD'].max()
unique_values, formation_new_values = np.unique(data['FORMATION'], return_inverse=True)
cmap_formations = colors.ListedColormap(formation_colors[unique_values], 'indexed')
cluster_f = formation_new_values.reshape(-1, 1)
fig = plt.figure(figsize=(3, 10))
ax = fig.add_subplot()
im_f = ax.imshow(cluster_f, extent=[0, 1, zbot, ztop],
interpolation='none', aspect='auto', cmap=cmap_formations, vmin=0, vmax=len(unique_values)-1)
ax.set_xlabel('FORMATION')
ax.set_xticks([])
divider_f = make_axes_locatable(ax)
cax_f = divider_f.append_axes("right", size="20%", pad=0.05)
cbar_f = plt.colorbar(im_f, cax=cax_f)
cbar_f.set_ticks(np.linspace(0, len(unique_values)-1, 2*len(unique_values)+1)[1::2])
cbar_f.set_ticklabels(formation_labels[unique_values])
plt.subplots_adjust(left=0.2, right=0.5)
plt.show()
Here is a comparison plot:
I can plot a world map with geopandas with:
world = geopandas.read_file(geopandas.datasets.get_path('naturalearth_lowres'))
fig, ax = plt.subplots()
world.plot(ax=ax, color=(0.8,0.5,0.5))
and it works fine, but I would like to center the map on a different longitude than the Prime Meridian. How do I do this?
This is how you can do it:
from shapely.geometry import LineString
from shapely.ops import split
from shapely.affinity import translate
import geopandas
world = geopandas.read_file(geopandas.datasets.get_path('naturalearth_lowres'))
def shift_map(shift):
shift -= 180
moved_map = []
splitted_map = []
border = LineString([(shift,90),(shift,-90)])
for row in world["geometry"]:
splitted_map.append(split(row, border))
for element in splitted_map:
items = list(element)
for item in items:
minx, miny, maxx, maxy = item.bounds
if minx >= shift:
moved_map.append(translate(item, xoff=-180-shift))
else:
moved_map.append(translate(item, xoff=180-shift))
gdf = geopandas.GeoDataFrame({"geometry":moved_map})
fig, ax = plt.subplots()
gdf.plot(ax=ax)
plt.show()
In the first step, you create your world and split it on a pre defined border of yours.
Then you get the bounds of all elements and check if the bounds match your desired shift. Afterwards you translate every element bigger than your border to the left side of the map and move all other elements to the right side, so that they aling with +180°.
This gives you for example:
A map shifted by 120°
Like in this question I needed to reset the centre of the map, but I also needed to move scatter plot network node positions that where bound to (long,lat) coordinates too.
I am hoping to save someone some time, as it's probably not obvious initially that to solve this problem you will have to wrangle some unfamiliar types.
Here is a method for shifting both the underlying map and some additional points:
import geopandas
world =
geopandas.read_file(geopandas.datasets.get_path('naturalearth_lowres'))
import matplotlib.pyplot as plt
import geopandas as gpd
from shapely.geometry import LineString
from shapely.ops import split
from shapely.affinity import translate
def shift_geom(shift, gdataframe,pos_all, plotQ=True):
# this code is adapted from answer found in SO
# will be credited here: ???
shift -= 180
moved_geom = []
splitted_geom = []
border = LineString([(shift,90),(shift,-90)])
for row in gdataframe["geometry"]:
splitted_geom.append(split(row, border))
for element in splitted_geom:
items = list(element)
for item in items:
minx, miny, maxx, maxy = item.bounds
if minx >= shift:
moved_geom.append(translate(item, xoff=-180-shift))
else:
moved_geom.append(translate(item, xoff=180-shift))
# got `moved_geom` as the moved geometry
moved_geom_gdf = gpd.GeoDataFrame({"geometry": moved_geom})
# can change crs here
if plotQ:
fig1, ax1 = plt.subplots(figsize=[8,6])
moved_geom_gdf.plot(ax=ax1)
plt.show()
df = pd.DataFrame({'Latitude': [xy[1] for xy in pos_all.values()],
'Longitude': [xy[0] for xy in pos_all.values()]})
gdf = geopandas.GeoDataFrame(df, geometry=geopandas.points_from_xy(df.Longitude, df.Latitude))
border2 = LineString([(shift,90),(shift,-90)])
geom = gdf.geometry.values
moved_map_points = []
moved_map_dict = {}
for element,key in zip(geom,list(pos_all.keys())):
if float(element.x) >= shift:
moved_map_points.append(translate(element, xoff=-180-shift))
else:
moved_map_points.append(translate(element, xoff=180-shift))
moved_map_dict[key] = (moved_map_points[-1].x,moved_map_points[-1].y)
return moved_geom_gdf,moved_map_dict
In this context pos_all are networkx node positions made of [(lat,long)]
shifted_world,moved_map_points = shift_geom(300, world,pos_all,plotQ= False)
I have three plots based on the same dataset. How can I link all three plots so that when I select a certain species in vbar plot, two scatter plot also change to plot points in that species only.
any help is appreciated~
from bokeh.sampledata.iris import flowers
from bokeh.plotting import figure, output_file, show
from bokeh.models import ColumnDataSource, CategoricalColorMapper
from bokeh.layouts import column, row
#color mapper to color data by species
mapper = CategoricalColorMapper(factors = ['setosa','versicolor', 'virginica'],\
palette = ['green', 'blue', 'red'])
output_file("plots.html")
#group by species and plot barplot for count
species = flowers.groupby('species')
source = ColumnDataSource(species)
p = figure(plot_width = 800, plot_height = 400, title = 'Count by Species', \
x_range = source.data['species'], y_range = (0,60),tools = 'box_select')
p.vbar(x = 'species', top = 'petal_length_count', width = 0.8, source = source,\
nonselection_fill_color = 'gray', nonselection_fill_alpha = 0.2,\
color = {'field': 'species', 'transform': mapper})
labels = LabelSet(x='species', y='petal_length_count', text='petal_length_count',
x_offset=5, y_offset=5, source=source)
p.add_layout(labels)
#scatter plot for sepal length and width
source1 = ColumnDataSource(flowers)
p1 = figure(plot_width = 800, plot_height = 400, tools = 'box_select', title = 'scatter plot for sepal')
p1.circle(x = 'sepal_length', y ='sepal_width', source = source1, \
nonselection_fill_color = 'gray', nonselection_fill_alpha = 0.2, \
color = {'field': 'species', 'transform': mapper})
#scatter plot for petal length and width
p2 = figure(plot_width = 800, plot_height = 400, tools = 'box_select', title = 'scatter plot for petal')
p2.circle(x = 'petal_length', y ='petal_width', source = source1, \
nonselection_fill_color = 'gray', nonselection_fill_alpha = 0.2, \
color = {'field': 'species', 'transform': mapper})
#show all three plots
show(column(p, row(p1, p2)))
I don't think there's some functionality existing for this at the moment. But you can explicitly link two ColumnDataSources with a CustomJS callback:
from bokeh.models import CusomJS
source = ColumnDataSource(species)
source1 = ColumnDataSource(flowers)
source.js_on_change('selected', CustomJS(args=dict(s1=source1), code="""
const indices = cb_obj.selected['1d'].indices;
const species = new Set(indices.map(i => cb_obj.data.species[i]));
s1.selected['1d'].indices = s1.data.species.reduce((acc, s, i) => {if (species.has(s)) acc.push(i); return acc}, []);
s1.select.emit();
"""))
Note that this callback only synchronizes selection from the bar plot to the scatter plots. To make selections on the scatter plots influence the bar plot, you'll have to write some additional code.