I have a code in python 3.11 for a contour plot generating from an excel table using matplotlib. The result shows only first days of months on the x axis (for example 1.6.2022, 1.7.2022 ...). I want all days from the excel source table. Her's the code:
import matplotlib.pyplot as plt
import numpy as np
from matplotlib.colors import Normalize
import pandas as pd
import matplotlib.dates as mdates
# import data from excel file
df = pd.read_excel('temperature_data.xlsx', index_col=0)
# Assign columns to variables
time = df.columns
depth = df.index
temperature = df.to_numpy()
# Creating the graph
fig, ax = plt.subplots()
min_temp = temperature.min()
max_temp = temperature.max()
cs = plt.contourf(time, depth, temperature, levels=np.arange(round(min_temp), round(max_temp)+2, 2), cmap='coolwarm', vmin=min_temp, vmax=max_temp)
cs2 = plt.contour(time, depth, temperature, levels=np.arange(round(min_temp), round(max_temp)+2, 2), colors='black')
plt.gca().invert_yaxis()
plt.clabel(cs2, inline=1, fontsize=10, fmt='%d')
plt.title('Teplota vody [°C]')
plt.xticks(rotation=90, ha='right')
ax.xaxis.set_major_formatter(mdates.DateFormatter('%d.%m.%Y'))
#ax.set_xlim(df.index.min(), df.index.max())
#ax.set_xlabel('Time')
ax.set_ylabel('hloubka [m]')
norm = Normalize(vmin=min_temp, vmax=max_temp)
plt.colorbar(cs, cmap='coolwarm', norm=norm)
plt.show()
Thank you for your help.
Related
I have three columns of data. They are too large to generate meshgrids from. So e.g. in order to generate a surface plot from the data, I use a method like so
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib import cm
from mpl_toolkits.mplot3d import Axes3D
x, y, z = np.loadtxt('data_file', unpack=True)
df = pd.DataFrame({'x':x, 'y':y, 'z':z})
fig = plt.figure()
ax = Axes3D(fig)
surf = ax.plot_trisurf(df.x, df.y, df.z, cmap=cm.jet, linewidth=0.05)
fig.colorbar(surf, shrink=0.5, aspect=5)
plt.show()
Is there a similar alternative to plot_trisurf for contours?
I want to divide and color points,val_lab(611,3) by their labels,pred_LAB(611,)
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure()
ax = plt.axes(projection = '3d')
ax.set_xlabel('L')
ax.set_ylabel('A')
ax.set_zlabel('B')
for i in range(0, len(val_lab)):
ax.scatter3D(
val_lab[i,0],
val_lab[i,1],
val_lab[i,2],
s = 8,
marker='o',
c = pred_LAB
#cmap = 'rainbow'
)
#ax.legend(*points.legend_elements(), title = 'clusters')
plt.show()
The problem is it shows error,
c' argument has 611 elements, which is not acceptable for use with 'x'
with size 1, 'y' with size 1.
However, if the dataset only have ten points,it can show the figure correctly, I don't know how to solve this problem, besides, how to add legend of this figure?
In your solution you would want to replace c = pred_LAB with c = pred_LAB[i]. But you do not have to use a for loop to plot the data. You can just use the following:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
# generate random input data
val_lab = np.random.randint(0,10,(611,3))
pred_LAB = np.random.uniform(0,1, (611,))
# plot data
fig = plt.figure()
ax = plt.axes(projection = '3d')
ax.set_xlabel('L')
ax.set_ylabel('A')
ax.set_zlabel('B')
# create one 3D scatter plot - no for loop
ax.scatter3D(
val_lab[:,0],
val_lab[:,1],
val_lab[:,2],
s = 8,
marker='o',
c = pred_LAB,
cmap = 'rainbow',
label='my points'
)
# add legend
plt.legend()
plt.show()
I want to fill the gridded map with colors based on the value of interest. A sample data is here:
import pandas as pd
df = pd.DataFrame()
df['lon'] = [100,105,110,115,120,125,130]
df['lat'] = [38,40,42,44,46,48,50]
df['value'] = [1,2,3,4,5,6,7]
Specifically, is it possible to do this with Cartopy? I found a similar question here:https://stackoverflow.com/questions/53412785/plotting-pandas-csv-data-onto-cartopy-map. But that post was to plot scattered points, I need to fill the grids with colors.
I myself tried:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import cartopy.crs as ccrs
lon, lat = np.meshgrid(df['lon'], df['lat'])
fig = plt.figure(figsize=[15,15])
ax = plt.axes(projection=ccrs.PlateCarree())
ax.pcolormesh(lon,lat,df['variable'],latlon=True,cmap='jet')
plt.show()
The error is at ax.pcolormesh(...), it says "not enough values to unpack (expected 2, got 1)"
Many thanks for your help.
For discrete data you can create rectangular patches for each point. Here is a possible solution for your sample data set. Each row of data (lat, long, value) is used to create a rectangular patch. The value is normalized by dividing with max(value) to enable using colormap for coloring the patches.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import cartopy.crs as ccrs
import matplotlib.patches as mpatches
def make_rect(clon, clat, dlon, dlat):
lon_min = clon - dlon/2.
lat_min = clat - dlat/2.
lon_max = clon + dlon/2.
lat_max = clat + dlat/2.
# clockwise from LL
#lons = [lon_min, lon_min, lon_max, lon_max, lon_min]
#lats = [lat_min, lat_max, lat_max, lat_min, lat_min]
ll = [lon_min,lat_min]
ul = [lon_min,lat_max]
ur = [lon_max,lat_max]
lr = [lon_max,lat_min]
return [ll, ul, ur, lr, ll]
df = pd.DataFrame()
df['lon'] = [100,105,110,115,120,125,130]
df['lat'] = [38,40,42,44,46,48,50]
df['value'] = [1,2,3,4,5,6,7] # not suffice for meshgrid plot
# The colormap to use.
cm = plt.cm.get_cmap('jet')
fig = plt.figure(figsize=[8,6])
ax = plt.axes(projection=ccrs.PlateCarree(), extent=[95, 134, 35, 52])
# plot the red dots using the available data
# comment out if not needed
ax.plot(df['lon'], df['lat'], 'ro')
# plot rectangular patches at the data points
dlon, dlat = 5, 2 #spacings between data points
for lon1, lat1, val1 in zip(df['lon'], df['lat'], df['value']):
pcorners = make_rect(lon1, lat1, dlon, dlat)
poly = mpatches.Polygon(pcorners, ec='gray', fill=True, lw=0.25, \
fc=cm(val1 / max(df['value'])), transform=ccrs.PlateCarree())
ax.add_patch(poly)
ax.gridlines(draw_labels=True)
plt.show()
The output plot:
Hi here is a sample code with 6 dimensional dataset.
import matplotlib.pyplot as plt
from matplotlib import cm
from matplotlib.ticker import LinearLocator, FormatStrFormatter
from mpl_toolkits.mplot3d import Axes3D
import numpy as np
import pandas as pd
import seaborn as sns
def f(a,b,c,d,e):
return a*b*c*d*e/1e14
# characteristics
a=np.arange(1000,11000,1000)
b=np.arange(45,100,10)
c=np.arange(10000,60000,5000)
d=np.arange(1,6,.5)*1000
e=np.array([1,2])
gr=np.array(np.meshgrid(a,b,c,d,e)).T.reshape(-1,5)
cost=np.array([f(*j) for j in gr])
df=pd.DataFrame(np.column_stack([gr,cost]),columns=['a','b','c','d','e','cost'])
I would like to look into possible trends in the data. For example i would like to know the effect of "a" on "cost" either while keeping the rest of the columns constant or not etc. Is there a better way of gaining insight from the data than this;
fig = plt.figure(figsize=[10,8])
ax = Axes3D(fig)
temp=df[(df.a==4000) & (df.d==1000)]
ax.plot_trisurf(temp.b, temp.c, temp.cost, cmap=cm.jet, linewidth=0.2)
ax.set_xlabel('b', fontsize=16)
ax.set_ylabel('c', fontsize=16)
ax.set_zlabel('cost', fontsize=16)
I have also tried these but not clear what they mean. For example, in this case shouldn't all correlation values be equal in the heat map for cost-variable pairs?
# Various visualizaiton methods
#a)
f, ax = plt.subplots(figsize=(10, 6))
corr = df.corr()
hm = sns.heatmap(round(corr,2), annot=True, ax=ax, cmap="coolwarm",fmt='.2f',
linewidths=.05)
f.subplots_adjust(top=0.93)
#b)
pd.plotting.scatter_matrix(df, alpha=0.2, figsize=(16, 16))
I have an hourly plot generated with matplotlib. I need to plot an event which goes for example, from 09:00 to 10:45. When I try to do it, using axvspan I obtain a bar from 9:00 to 10:00. How could I obtain the longer one?
import matplotlib.pyplot as plt
from matplotlib.gridspec import GridSpec
import datetime as dt
import pandas as pd
now_date = dt.datetime(2018,10,1,9)
d_tw_ini = now_date - dt.timedelta(hours = 1)
d_tw_fin = now_date + dt.timedelta(hours = 3)
dts = pd.date_range(start=d_tw_ini, end=d_tw_fin, freq='1H', name='ini', closed='left')
data=pd.DataFrame({'val':[0.5,0.4,0.7,0.9]})
ev1=[dt.datetime(2018,10,1,9,5),dt.datetime(2018,10,1,10,50)]
data['t']=dts.values
data.set_index('t',inplace=True)
fig = plt.figure()
gs = GridSpec(1, 1)
ax_1 = fig.add_subplot(gs[0, 0])
data.plot(ax=ax_1, y='val')
ax_1.axvspan(ev1[0],ev1[1], alpha=0.3, color= 'red')
Result
Juan, it looks when you used pandas to plot, the hourly indexing seems to cause issues with how axvspan gets plotted.
I replaced
data.plot(ax=ax_1, y='val')
with
ax_1.plot(data.index, data['val'])
which generates the image below, but unfortunately you lose the automated x-axis formatting.
Adding the two lines below will result in the same date formatting as your example.
ax_1.set_xticks([x for x in data.index])
ax_1.set_xticklabels([str(x)[11:16] for x in data.index])
Below is the full code to produce the above plot.
import matplotlib.pyplot as plt
from matplotlib.gridspec import GridSpec
import datetime as dt
import pandas as pd
now_date = dt.datetime(2018,10,1,9)
d_tw_ini = now_date - dt.timedelta(hours = 1)
d_tw_fin = now_date + dt.timedelta(hours = 3)
dts = pd.date_range(start=d_tw_ini, end=d_tw_fin, freq='1h', name='ini',
closed='left')
data=pd.DataFrame({'val':[0.5,0.4,0.7,0.9]})
ev1=[dt.datetime(2018,10,1,9,5,0),dt.datetime(2018,10,1,10,50,0)]
data['t']=dts.values
data.set_index('t',inplace=True)
fig = plt.figure()
gs = GridSpec(1, 1)
ax_1 = fig.add_subplot(gs[0, 0])
# modified section below
ax_1.plot(data.index, data['val'])
ax_1.axvspan(ev1[0],ev1[1], alpha=0.3, color= 'red')
ax_1.set_xticks([x for x in data.index])
ax_1.set_xticklabels([str(x)[11:16] for x in data.index])
plt.show()