I'm working on using a for loop to produce graphs for each set of data I have. Each plot prints correctly however the savefig() portion of my code only saves the last plot under each file name.
Here is a section of my code
total = 3
idx_list = []
dct = {}
for i, df in enumerate(graph_list):
data = pd.DataFrame(df)
for idx, v in enumerate(data['content'].unique()):
dct[f'x{idx}'] = data.loc[data['content'] == v]
idx_list.append(idx)
xs = dct[f'x{idx}'].Time
yB = dct[f'x{idx}'].Weight
yA = dct[f'x{idx}'].Height
fig, ax = plt.subplots(figsize =(10,8))
legends = ['Weight', 'Height']
ax.plot(xs, yB, linestyle = ':', color ='#4c4c4c', linewidth = 4.0)
ax.plot(xs, yA, color = '#fac346', linewidth = 3.0)
ax.legend(legends, loc = 'lower center', ncol = len(legends), bbox_to_anchor = (0.5, -0.15), frameon = False)
ax.yaxis.set_major_formatter(mtick.PercentFormatter(xmax=1, decimals = None, symbol ='%', is_latex = False))
ax.set_xticks(xs[::4])
ax.tick_params(axis = 'x', labelrotation = 45, labelsize = 10)
ax.yaxis.grid()
new_idx = [x+1 for x in idx_list]
for graph in range(total+1):
if graph != 0:
for ids in set(new_idx):
print('Graph {0} ID {1}'.format(graph, ids))
fig.savefig('Graph {0} ID {1}.jpg'.format(graph, ids))
I want each graph to save under the file names:
Graph 1 ID 1
Graph 1 ID 2
Graph 2 ID 1
Graph 2 ID 2
Graph 3 ID 1
Graph 3 ID 2
Thanks for any help you can provide!
You do not keep a reference to each figure, so when you call fig.savefig in the final loop you are actually saving the figure referenced by fig (which is the last figure) each time. There are many ways to manage this: you can save the figure in the same loop that created it, you can assign a unique name to each figure, or you can keep a reference to each figure in a list. The first option is simpler:
dct = {} # I assume this dict is used for something after saving the figures. Otherwise it is not necessary
for i, df in enumerate(graph_list):
data = pd.DataFrame(df)
for idx, v in enumerate(data['content'].unique()):
dct[f'x{idx}'] = data.loc[data['content'] == v]
xs = dct[f'x{idx}'].Time
yB = dct[f'x{idx}'].Weight
yA = dct[f'x{idx}'].Height
fig, ax = plt.subplots(figsize=(10, 8))
legends = ['Weight', 'Height']
ax.plot(xs, yB, linestyle=':', color='#4c4c4c', linewidth=4.0)
ax.plot(xs, yA, color='#fac346', linewidth=3.0)
ax.legend(legends, loc='lower center', ncol=len(legends),
bbox_to_anchor=(0.5, -0.15), frameon=False)
ax.yaxis.set_major_formatter(mtick.PercentFormatter(xmax=1,
decimals=None, symbol='%', is_latex=False))
ax.set_xticks(xs[::4])
ax.tick_params(axis='x', labelrotation=45, labelsize=10)
ax.yaxis.grid()
print('Graph {0} ID {1}'.format(i+1, idx+1))
fig.savefig('Graph {0} ID {1}.jpg'.format(i+1, idx+1))
plt.close(fig) # if you do not need to leave the figures open
Related
I try to plot lines in a loop,but its connecting it,i tried many variants,but cand understand and find the answer,maybe the dataframe
im a newbie in Matplotlib
the code of method:
self.testnewnewventnest[Debit] - is a nested dict with the data i need for plotting
def showmainplot(self):
for Debit in self.Debitlist:
self.Presinit = self.VentTable.loc[Debit]
self.Tinit= float(self.Tinit)
self.Presinit=int(float(self.Presinit))
self.Powinit = float(self.Powinit)
x = symbols("x")
for Turatie in self.Tfin:
eqPres = (Turatie/self.Tinit)*(Turatie/self.Tinit)*self.Presinit-x
PresFin = solve(eqPres)
eqDebit = (Turatie/self.Tinit)*int(Debit)
DebitFin = solve(eqDebit)
eqPow = (Turatie/self.Tinit)*(Turatie/self.Tinit)*(Turatie/self.Tinit)*float(self.Powinit)
self.TestnewVentnest['KW'] = float(eqPow)
self.TestnewVentnest['Turatie'] = Turatie
self.TestnewVentnest['Presiune'] = float(PresFin[0])
self.TestnewVent[float(eqDebit)] = dict(self.TestnewVentnest)
self.testnewnewventnest[Debit] = dict(self.TestnewVent)
print(self.testnewnewventnest)
axeslist = []
n=0
fig, ax = plt.subplots(figsize=(5, 5))
ax1 = ax.twinx()
ax1.spines.right.set_position(("axes", 1.06))
ax.set_xlabel("Debit")
for dicts in self.testnewnewventnest:
Ventdataframe = pd.DataFrame(self.testnewnewventnest[dicts])
print(Ventdataframe)
ax2 = plt.subplot()
fig, ax = plt.subplots(figsize=(5, 5))
ax1 = ax.twinx()
ax1.spines.right.set_position(("axes", 1.06))
ax.set_xlabel("Debit")
axeslist.append(plt.subplot())
# print(df.iloc[0])
# ax1.set_ylabel("Turatie")
# ax.set_ylabel("Presiune")
# Ventdataframe.plot(Ventdataframe.loc["Presiune"], color="b",label="Presiune"+str(n),marker = 'o')
Ventdataframe.loc["Presiune"].plot(color="b",label="Presiune"+str(n),marker = 'o')
n+=1
# ax2 = ax.twinx()
# ax2.set_ylabel('KW')
# ax1.plot(Ventdataframe.loc["Turatie"],color='#000000',label="Turatie",marker = 'o')
# ax2.plot(Ventdataframe.loc["KW"], color='r',label="KW",marker = 'o')
# ax1.grid()
# ax2.yaxis.set_major_locator(FixedLocator(Ventdataframe.loc["KW"]))
# ax.yaxis.set_major_locator(FixedLocator(Ventdataframe.loc["Presiune"]))
# ax1.yaxis.set_major_locator(FixedLocator(self.Tfin))
# ax.xaxis.set_major_locator(FixedLocator(Ventdataframe.columns))
# lc = matpl.ticker.NullLocator()
# ax.yaxis.set_major_locator(lc)
plt.show()
and the self.testnewnewventnest look like:
Yes,the problem was in the loop,and in the dictionaries,in every iteration he added all previous dictionaries from iterations
I would put that in a dataframe and do it like this.
uniques = df['ID'].unique()
for i in uniques:
fig, ax = plt.subplots()
fig.set_size_inches(4,3)
df_single = df[df['ID']==i]
sns.lineplot(data=df_single, x='Month', y='Expense')
ax.set(xlabel='Time', ylabel='Total Expense')
plt.xticks(rotation=45)
plt.show()
I am attempting to plot multiple line graphs in a graph table itself. However, I run into an error that mentioned:
No artists with labels found to put in legend. Note that artists whose label start with an underscore are ignored when legend() is called with no argument.
Not only this happened but my legend tables of the 3 lines don't merge together and my X-axis does not show the months but random numbers from my dataframe. Here is my code and graph result to look through.
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
df = pd.read_excel (r'C:\Users\admin\Desktop\Question Folder\Sales of top 30 customers.xlsx')
#Refine and adjust the dataframe for suitable manipulation
df = df.drop('Unnamed: 0', axis = 1)
df = df.iloc[2: , :]
row_detail = df.head(1).values.tolist()
row_detail = row_detail[0]
a = df.iloc[-3:, :].values.tolist()
a = a[0]
df.columns = row_detail
df = df.iloc[1:, :]
print(df) # This is for checking purpose
# This creates a dataframe needed for the practice
df1 = df.iloc[:3]
# This is to plot a line graph from df1
df_chosen = df1
a = 0
# Turning data row of a customer into a list
data_row_1 = df_chosen.iloc[a].values.tolist()
data_row_2 = df_chosen.iloc[a + 1].values.tolist()
data_row_3 = df_chosen.iloc[a + 2].values.tolist()
date = data_row_1[1:]
cus_1 = data_row_1[0]
cus_2 = data_row_2[0]
cus_3 = data_row_3[0]
y1 = data_row_1[1:]
y2 = data_row_2[1:]
y3 = data_row_3[1:]
x = np.arange(len(date)) # the label locations
width = 0.60 # the width of the bars
fig, ax = plt.subplots()
# Increase size of plot in jupyter
plt.rcParams["figure.figsize"] = (20,15)
plt.rcParams.update({'font.size':25})
# Add some text for labels, title and custom x-axis tick labels, etc.
ax.set_xlabel('Months', fontsize=30)
ax.set_ylabel('Sales', fontsize=30)
ax.set_title('Monthly Sales from ' + cus_1 +", " + cus_2+ " and " + cus_3, fontsize=30)
ax.set_xticks(x, date)
ax.set_ylim(bottom = 0, top = 1000)
legend1 = plt.legend(())
ax.legend(loc='best', fontsize=30)
plt.grid(True)
# set up the 1st line graph
ax.plot(x, y1, "r", label = cus_1, marker='x')
#ax.set_yticks(
ax.grid(True) # turn on grid #1
ax.set_ylim(bottom = 0, top = 1000)
ax.legend(loc='upper left', fontsize=25)
ax2 = ax.twinx()
ax2.plot(x, y2, "b", label= cus_2, marker='x')
ax2.set_yticks([])
ax2.grid(False) # turn off grid #2
ax2.set_ylim(bottom = 0, top = 10000)
ax2.legend(loc='upper left', fontsize=25)
ax3 = ax2.twinx()
ax3.plot(x, y3, "g", label= cus_3, marker='x')
ax3.set_yticks([])
ax3.grid(False) # turn off grid #2
ax3.set_ylim(bottom = 0, top = 10000)
ax3.legend(loc='upper left', fontsize=25)
I just need to understand and know the solutions for the following:
Why is the X-axis not showing the months' names?
Why is the 3 separate legend tables not connected together?
How do I avoid the 'No artists with labels found to put in legend. Note that artists whose label start with an underscore are ignored when legend() is called with no argument.' error warning?
Hope to receive a favorable reply soon. :)
Edit notice: Here is the dataframe used for this problem:
I'm struggling to adjust my plot legend after adding the axline/ hline on 100 level in the graph.(screenshot added)
if there's a way to run this correctly so no information will be lost in legend, and maybe add another hline and adding it to the legend.
adding the code here, maybe i'm not writing it properly.
fig, ax1 = plt.subplots(figsize = (9,6),sharex=True)
BundleFc_Outcome['Spend'].plot(kind = 'bar',color = 'blue',width = 0.4, ax = ax1,position = 1)
#
# Make the y-axis label, ticks and tick labels match the line color.
ax1.set_ylabel('SPEND', color='b', size = 18)
ax1.set_xlabel('Bundle FC',color='w',size = 18)
ax2 = ax1.twinx()
ax2.set_ylabel('ROAS', color='r',size = 18)
ax1.tick_params(axis='x', colors='w',size = 20)
ax2.tick_params(axis = 'y', colors='w',size = 20)
ax1.tick_params(axis = 'y', colors='w',size = 20)
#ax1.text()
#
ax2.axhline(100)
BundleFc_Outcome['ROAS'].plot(kind = 'bar',color = 'red',width = 0.4, ax = ax2,position = 0.25)
plt.grid()
#ax2.set_ylim(0, 4000)
ax2.set_ylim(0,300)
plt.title('ROAS & SPEND By Bundle FC',color = 'w',size= 20)
plt.legend([ax2,ax1],labels = ['SPEND','ROAS'],loc = 0)
The code gives me the following picture:
After implementing the suggestion in the comments, the picture looks like this (does not solve the problem):
You can use bbox_to_anchor attribute to set legend location manually.
ax1.legend([ax1],labels = ['SPEND'],loc='upper right', bbox_to_anchor=(1.25,0.70))
plt.legend([ax2,ax1],labels = ['SPEND','ROAS'],loc='upper right', bbox_to_anchor=(1.25,0.70))
https://matplotlib.org/users/legend_guide.html#legend-location
So finally figured it out , was simpler for a some reason
Even managed to add another threshold at level 2 for minimum spend.
fig, ax1 = plt.subplots(figsize = (9,6),sharex=True)
BundleFc_Outcome['Spend'].plot(kind = 'bar',color = 'blue',width = 0.4, ax = ax1,position = 1)
#
# Make the y-axis label, ticks and tick labels match the line color.
ax1.set_ylabel('SPEND', color='b', size = 18)
ax1.set_xlabel('Region',color='w',size = 18)
ax2 = ax1.twinx()
ax2.set_ylabel('ROAS', color='r',size = 18)
ax1.tick_params(axis='x', colors='w',size = 20)
ax2.tick_params(axis = 'y', colors='w',size = 20)
ax1.tick_params(axis = 'y', colors='w',size = 20)
#ax1.text()
#
BundleFc_Outcome['ROAS'].plot(kind = 'bar',color = 'red',width = 0.4, ax = ax2,position = 0.25)
plt.grid()
#ax2.set_ylim(0, 4000)
ax2.set_ylim(0,300)
plt.title('ROAS & SPEND By Region',color = 'w',size= 20)
fig.legend([ax2,ax1],labels = ['SPEND','ROAS'],loc = 0)
plt.hlines([100,20],xmin = 0,xmax = 8,color= ['r','b'])
I don't recommend using the builtin functions of pandas to do more complex plotting. Also when asking a question it is common courtesy to provide a minimal and verifiable example (see here). I took the liberty to simulate your problem.
Due to the change in axes, we need to generate our own legend. First the results:
Which can be achieved with:
import matplotlib.pyplot as plt, pandas as pd, numpy as np
# generate dummy data.
X = np.random.rand(10, 2)
X[:,1] *= 1000
x = np.arange(X.shape[0]) * 2 # xticks
df = pd.DataFrame(X, columns = 'Spend Roast'.split())
# end dummy data
fig, ax1 = plt.subplots(figsize = (9,6),sharex=True)
ax2 = ax1.twinx()
# tmp axes
axes = [ax1, ax2] # setup axes
colors = plt.cm.tab20(x)
width = .5 # bar width
# generate dummy legend
elements = []
# plot data
for idx, col in enumerate(df.columns):
tax = axes[idx]
tax.bar(x + idx * width, df[col], label = col, width = width, color = colors[idx])
element = tax.Line2D([0], [0], color = colors[idx], label = col) # setup dummy label
elements.append(element)
# desired hline
tax.axhline(200, color = 'red')
tax.set(xlabel = 'Bundle FC', ylabel = 'ROAST')
axes[0].set_ylabel('SPEND')
tax.legend(handles = elements)
As you can see in the picture attached when I execute my code I get two graphs and one of them is empty. I only need one so what is wrong with my code below?
kmf_par_modele = KaplanMeierFitter()
duration = iot_df_2.duree
observed = iot_df_2.batterie_0
fig, axes = plt.subplots(nrows = 1, ncols = 2, sharey = True, figsize=(12,15))
for modele_capteur, ax in zip(modele_capteur, axes.flatten()):
idx = iot_df_2.modele_objet == modele_capteur
kmf_par_modele.fit(duration[idx], observed[idx])
kmf_par_modele.plot(ax=ax, legend=False)
ax.annotate("Moyenne = {:.0f} mois".format(kmf_par_modele.median_), xy = (.47, .85), xycoords = "axes fraction")
ax.set_xlabel("")
ax.set_title(modele_capteur)
ax.set_xlim(0,25)
ax.set_ylim(0,1)
fig.tight_layout()
fig.text(0.5, -0.01, "Timeline (Mois)", ha="center")
fig.text(-0.01, 0.5, "Probabilité qu'un ERS_C02 ait toujours de la batterie", va="center", rotation="vertical")
fig.suptitle("Courbe de longévité pour le capteur ERS_C02",
fontsize=20)
fig.subplots_adjust(top=0.92)
plt.show()
As I mentioned in my comments, you just need to specify one single plot (subplot) if you only need one. I am answering because you don't need to flatten your axes instance because you just use a single figure. Here is how you can do it alternatively:
fig = plt.figure(figsize=(12,15))
ax = fig.add_subplot(111) # 111 means 1 row, 1 column ad 1st subplot (here only 1)
for modele_capteur in modele_capteur: # just loop over your modele_capteur
idx = iot_df_2.modele_objet == modele_capteur
kmf_par_modele.fit(duration[idx], observed[idx])
kmf_par_modele.plot(ax=ax, legend=False)
ax.annotate("Moyenne = {:.0f} mois".format(kmf_par_modele.median_), xy = (.47, .85), xycoords = "axes fraction")
ax.set_xlabel("")
ax.set_title(modele_capteur)
ax.set_xlim(0,25)
ax.set_ylim(0,1)
I have the following code:
import matplotlib.pyplot as plt
import numpy as np
np.random.seed(123456)
import pandas as pd
df = pd.DataFrame(3 * np.random.rand(4, 4), index=['a', 'b', 'c', 'd'],
columns=['x', 'y','z','w'])
plt.style.use('ggplot')
colors = plt.rcParams['axes.color_cycle']
fig, axes = plt.subplots(nrows=2, ncols=3)
for ax in axes.flat:
ax.axis('off')
for ax, col in zip(axes.flat, df.columns):
ax.pie(df[col], labels=df.index, autopct='%.2f', colors=colors)
ax.set(ylabel='', title=col, aspect='equal')
axes[0, 0].legend(bbox_to_anchor=(0, 0.5))
fig.savefig('your_file.png') # Or whichever format you'd like
plt.show()
Which produce the following:
My question is, how can I remove the label based on a condition. For example I'd only want to display labels with percent > 20%. Such that the labels and value of a,c,d won't be displayed in X, etc.
The autopct argument from pie can be a callable, which will receive the current percentage. So you only would need to provide a function that returns an empty string for the values you want to omit the percentage.
Function
def my_autopct(pct):
return ('%.2f' % pct) if pct > 20 else ''
Plot with matplotlib.axes.Axes.pie
fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(8, 6))
for ax, col in zip(axes.flat, df.columns):
ax.pie(df[col], labels=df.index, autopct=my_autopct)
ax.set(ylabel='', title=col, aspect='equal')
fig.tight_layout()
Plot directly with the dataframe
axes = df.plot(kind='pie', autopct=my_autopct, figsize=(8, 6), subplots=True, layout=(2, 2), legend=False)
for ax in axes.flat:
yl = ax.get_ylabel()
ax.set(ylabel='', title=yl)
fig = axes[0, 0].get_figure()
fig.tight_layout()
If you need to parametrize the value on the autopct argument, you'll need a function that returns a function, like:
def autopct_generator(limit):
def inner_autopct(pct):
return ('%.2f' % pct) if pct > limit else ''
return inner_autopct
ax.pie(df[col], labels=df.index, autopct=autopct_generator(20), colors=colors)
For the labels, the best thing I can come up with is using list comprehension:
for ax, col in zip(axes.flat, df.columns):
data = df[col]
labels = [n if v > data.sum() * 0.2 else ''
for n, v in zip(df.index, data)]
ax.pie(data, autopct=my_autopct, colors=colors, labels=labels)
Note, however, that the legend by default is being generated from the first passed labels, so you'll need to pass all values explicitly to keep it intact.
axes[0, 0].legend(df.index, bbox_to_anchor=(0, 0.5))
For labels I have used:
def my_level_list(data):
list = []
for i in range(len(data)):
if (data[i]*100/np.sum(data)) > 2 : #2%
list.append('Label '+str(i+1))
else:
list.append('')
return list
patches, texts, autotexts = plt.pie(data, radius = 1, labels=my_level_list(data), autopct=my_autopct, shadow=True)
You can make the labels function a little shorter using list comprehension:
def my_autopct(pct):
return ('%1.1f' % pct) if pct > 1 else ''
def get_new_labels(sizes, labels):
new_labels = [label if size > 1 else '' for size, label in zip(sizes, labels)]
return new_labels
fig, ax = plt.subplots()
_,_,_ = ax.pie(sizes, labels=get_new_labels(sizes, labels), colors=colors, autopct=my_autopct, startangle=90, rotatelabels=False)