I have the following dataframe:
I want to make a 3D scatter plot in plotly of the principal components. Something like:
I have been strugglingin the edition of the properties of the plot. I would like to know:
How to edit the hover in order to print Muestra,pc1,pc2,pc3 instead of x,y,z?
How to add the legend outside the plot?
How to edit the name of the axis?
CODE:
import pandas as pd
import string
import plotly.graph_objects as go
df = pd.DataFrame(
{
"pc1": range(11),
"pc2": range(10, -1, -1),
'pc3': range(35,46),
"Muestra": list(string.ascii_uppercase[:11]),
"color": ["#cf0c0c"] * 6 + ["#0dab51"] * 5,
},
index=range(1, 12))
data = go.Scatter3d(x=df.pc1,
y=df.pc2,
z=df.pc3,
mode='markers',
marker=dict(size=10, color=df.color, opacity=0.8))
fig = go.Figure(data=[data])
# tight layout
fig.update_layout(margin=dict(l=0, r=0, b=0, t=0))
fig.show()
Related
Is it possible to draw a trendline with Plotly line graph?
figure = px.line(x=year_week, y=num_accidents,
labels=dict(time_from_db="Time",
num_accidents="Num of Accidents"),
title="Number of Accidents Per Week", line_shape='spline',
trendline="ols")
The above code does not work unless I remove trendline="old".
you can do this using px.scatter instead of px.line;
You just need to update your figure object and change the mode to lines, as:
fig.update_traces(mode = 'lines')
Full code
import pandas as pd
import plotly.express as px
# data
df = px.data.stocks()[['GOOG', 'AAPL']]
# your choices
target = 'GOOG'
# plotly
fig = px.scatter(df,
x=target,
y=[c for c in df.columns if c != target],
trendline='ols',
title="trendline example")
fig.update_traces(mode='lines')
fig.data[-1].line.color='green'
fig
I hope it can solve your problem.
Regards,
Leonardo
I want to create GUI which should automatically clean data in csv file once selected and plot superimposed PDF & histogram graph. I have uploaded basic python program which generates the required graph but I am unbale to convert it into interface. I guess, only "open file" & "plot" buttons would suffice the requirement. image- want to retrieve data from 'N'th column (13) only with skipping top 4 rows
I am basically from metallurgy background and trying my hands in this field.
Any help would be greatly appreciated
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import norm
raw_data = pd.read_csv("D:/Project/Python/NDC/Outlier_ND/800016_DAT.csv",skiprows=4,header=None)
clean = pd.DataFrame(raw_data)
data1 = clean.iloc[:, [13]]
Q1 = data1.quantile(0.25)
Q3 = data1.quantile(0.75)
IQR = Q3 - Q1
data_IQR = data1[~((data1 < (Q1 - 1.5 * IQR)) |(data1 > (Q3 + 1.5 * IQR))).any(axis=1)]
data_IQR.shape
print(data1.shape)
print(data_IQR.shape)
headerList = ['Actual_MR']
data_IQR.to_csv(r'D:\Project\Python\NDC\Outlier_ND\800016_DAT_IQR.csv', header=headerList, index=False)
data = pd.read_csv("D:/Project/Python/NDC/Outlier_ND/800016_DAT_IQR.csv")
mean, sd = norm.fit(data)
plt.hist(data, bins=25, density=True, alpha=0.6, facecolor = '#2ab0ff', edgecolor='#169acf', linewidth=0.5)
xmin, xmax = plt.xlim()
x = np.linspace(xmin, xmax, 100)
p = norm.pdf(x, mean, sd)
plt.plot(x, p, 'red', linewidth=2)
title = " Graph \n mean: {:.2f} and SD: {:.2f}".format(mean, sd)
plt.title(title)
plt.xlabel('MR')
plt.ylabel('Pr')
plt.show()
Following code demo how PySimpleGUI to work with matplotlib, detail please find all remark in script.
import math, random
from pathlib import Path
from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg
from matplotlib.figure import Figure
import PySimpleGUI as sg
# 1. Define the class as the interface between matplotlib and PySimpleGUI
class Canvas(FigureCanvasTkAgg):
"""
Create a canvas for matplotlib pyplot under tkinter/PySimpleGUI canvas
"""
def __init__(self, figure=None, master=None):
super().__init__(figure=figure, master=master)
self.canvas = self.get_tk_widget()
self.canvas.pack(side='top', fill='both', expand=1)
# 2. create PySimpleGUI window, a fixed-size Frame with Canvas which expand in both x and y.
font = ("Courier New", 11)
sg.theme("DarkBlue3")
sg.set_options(font=font)
layout = [
[sg.Input(expand_x=True, key='Path'),
sg.FileBrowse(file_types=(("ALL CSV Files", "*.csv"), ("ALL Files", "*.*"))),
sg.Button('Plot')],
[sg.Frame("", [[sg.Canvas(background_color='green', expand_x=True, expand_y=True, key='Canvas')]], size=(640, 480))],
[sg.Push(), sg.Button('Exit')]
]
window = sg.Window('Matplotlib', layout, finalize=True)
# 3. Create a matplotlib canvas under sg.Canvas or sg.Graph
fig = Figure(figsize=(5, 4), dpi=100)
ax = fig.add_subplot()
canvas = Canvas(fig, window['Canvas'].Widget)
# 4. initial for figure
ax.set_title(f"Sensor Data")
ax.set_xlabel("X axis")
ax.set_ylabel("Y axis")
ax.set_xlim(0, 1079)
ax.set_ylim(-1.1, 1.1)
ax.grid()
canvas.draw() # do Update to GUI canvas
# 5. PySimpleGUI event loop
while True:
event, values = window.read()
if event in (sg.WINDOW_CLOSED, 'Exit'):
break
elif event == 'Plot':
"""
path = values['Path']
if not Path(path).is_file():
continue
"""
# 6. Get data from path and plot from here
ax.cla() # Clear axes first if required
ax.set_title(f"Sensor Data")
ax.set_xlabel("X axis")
ax.set_ylabel("Y axis")
ax.grid()
theta = random.randint(0, 359)
x = [degree for degree in range(1080)]
y = [math.sin((degree+theta)/180*math.pi) for degree in range(1080)]
ax.plot(x, y)
canvas.draw() # do Update to GUI canvas
# 7. Close window to exit
window.close()
I have an animated graph that I update in a clientside callback. However, I want to update the text as well as the x and y values of the traces in Graph.extendData(), but it seems that that doesn't work. Is there something I'm missing? Alternatively, is there a different method I should be using instead?
Adopting the code from this post (Plotly/Dash display real time data in smooth animation), I'd like something like this, but where updating the text with extendData actually worked:
import dash
import dash_html_components as html
import dash_core_components as dcc
import numpy as np
from dash.dependencies import Input, Output, State
# Example data (a circle).
resolution = 1000
t = np.linspace(0, np.pi * 2, resolution)
x, y = np.cos(t), np.sin(t)
text = str(t)
# Example app.
figure = dict(data=[{'x': [], 'y': []}], text = [], layout=dict(xaxis=dict(range=[-1, 1]), yaxis=dict(range=[-1, 1])))
app = dash.Dash(__name__, update_title=None) # remove "Updating..." from title
app.layout = html.Div([
dcc.Graph(id='graph', figure=dict(figure)), dcc.Interval(id="interval", interval=25),
dcc.Store(id='offset', data=0), dcc.Store(id='store', data=dict(x=x, y=y, text=text, resolution=resolution)),
])
# This makes the graph fail to draw instead of just extending the text as wel!
app.clientside_callback(
"""
function (n_intervals, data, offset) {
offset = offset % data.x.length;
const end = Math.min((offset + 10), data.x.length);
return [[{x: [data.x.slice(offset, end)], y: [data.y.slice(offset, end)], text: [data.text.slice(offset, end)]}, [0], 500], end]
}
""",
[Output('graph', 'extendData'), Output('offset', 'data')],
[Input('interval', 'n_intervals')], [State('store', 'data'), State('offset', 'data')]
)
if __name__ == '__main__':
app.run_server()
Alternatively, is there a different method I should be using instead?
I was googl'ing around trying to find solution for the following question (no luck so far). I am using Plotly Dash callback in order to build a graph:
#app.callback(
Output("graph", "figure"),
[Input("some-input", "value")],
[State("some-state", "value")])
def build_graph(input_value, state_value):
// computing data for graph_figure
return graph_figure
Now, I want to have another callback which will highlight a specific point on the graph (or add/remove a point) based on some input condition. I struggle to figure out what to use for Output in this case? Because I cannot output graph.figure again (Dash does not allow output to the same component from different callbacks). And re-drawing entire graph seems to be inefficient.
I will appreciate any suggestions.
It is possible to change the layout of your graph without redrawing the whole graph by using this library: https://github.com/jimmybow/mydcc
There is an example how to use it here: https://github.com/jimmybow/mydcc#3-mydccrelayout-
I have prepared a small example that adds an annotation on button click. Don't forget to pip install mydcc beforehand. I had to add a cache - in form of an invisible div - to preserve the old annotations when adding a new one.
import dash
import dash_core_components as dcc
import dash_html_components as html
import mydcc
import random
import json
external_stylesheets = ['https://codepen.io/chriddyp/pen/bWLwgP.css']
app = dash.Dash(__name__, external_stylesheets=external_stylesheets)
initial_layout = {'title': 'Dash Data Visualization'}
app.layout = html.Div(children=[
html.H1(children='Hello Dash'),
html.Div(children='''
Dash: A web application framework for Python.
'''),
dcc.Graph(
id='example-graph',
figure={
'data': [{'x': [1, 2, 3], 'y': [4, 1, 2], 'name': 'Test'}],
'layout': initial_layout
}
),
mydcc.Relayout(id="rrr", aim='example-graph'),
html.Button('Add random annotation', id='button'),
html.Div(id='user-cache', style={'display': 'none'},
children=json.dumps(initial_layout)),
])
#app.callback(
[dash.dependencies.Output('rrr', 'layout'),
dash.dependencies.Output('user-cache', 'children')],
[dash.dependencies.Input('button', 'n_clicks')],
[dash.dependencies.State('user-cache', 'children')])
def update_graph_annotations(n_clicks, layout):
if n_clicks is not None:
layout = json.loads(layout)
if not 'annotations' in layout:
layout['annotations'] = []
layout['annotations'].append(dict(
x=random.uniform(0, 1) * 2 + 1,
y=random.uniform(0, 1) * 2 + 1,
xref="x",
yref="y",
text="Annotation" + str(n_clicks),
showarrow=True
))
return layout, json.dumps(layout)
return dash.no_update, dash.no_update
if __name__ == '__main__':
app.run_server(debug=True)
I've been trying for weeks to plot 3 sets of (x, y) data on the same plot from a .CSV file, and I'm getting nowhere. My data was originally an Excel file which I have converted to a .CSV file and have used pandas to read it into IPython as per the following code:
from pandas import DataFrame, read_csv
import pandas as pd
# define data location
df = read_csv(Location)
df[['LimMag1.3', 'ExpTime1.3', 'LimMag2.0', 'ExpTime2.0', 'LimMag2.5','ExpTime2.5']][:7]
My data is in the following format:
Type mag1 time1 mag2 time2 mag3 time3
M0 8.87 41.11 8.41 41.11 8.16 65.78;
...
M6 13.95 4392.03 14.41 10395.13 14.66 25988.32
I'm trying to plot time1 vs mag1, time2 vs mag2 and time3 vs mag3, all on the same plot, but instead I get plots of time.. vs Type, eg. for the code:
df['ExpTime1.3'].plot()
I get 'ExpTime1.3' (y-axis) plotted against M0 to M6 (x-axis), when what I want is 'ExpTime1.3' vs 'LimMag1.3', with x-labels M0 - M6.
How do I get 'ExpTime..' vs 'LimMag..' plots, with all 3 sets of data on the same plot?
How do I get the M0 - M6 labels on the x-axis for the 'LimMag..' values (also on the x-axis)?
Since trying askewchan's solutions, which did not return any plots for reasons unknown, I've found that I can get a plot of ExpTimevs LimMagusing df['ExpTime1.3'].plot(),if I change the dataframe index (df.index) to the values of the x axis (LimMag1.3). However, this appears to mean that I have to convert each desired x-axis to the dataframe index by manually inputing all the values of the desired x-axis to make it the data index. I have an awful lot of data, and this method is just too slow, and I can only plot one set of data at a time, when I need to plot all 3 series for each dataset on the one graph. Is there a way around this problem? Or can someone offer a reason, and a solution, as to why I I got no plots whatsoever with the solutions offered by askewchan?\
In response to nordev, I have tried the first version again, bu no plots are produced, not even an empty figure. Each time I put in one of the ax.plotcommands, I do get an output of the type:
[<matplotlib.lines.Line2D at 0xb5187b8>], but when I enter the command plt.show()nothing happens.
When I enter plt.show()after the loop in askewchan's second solution, I get an error back saying AttributeError: 'function' object has no attribute 'show'
I have done a bit more fiddling with my original code and can now get a plot of ExpTime1.3vs LimMag1.3 with the code df['ExpTime1.3'][:7].plot(),by making the index the same as the x axis (LimMag1.3), but I can't get the other two sets of data on the same plot. I would appreciate any further suggestions you may have. I'm using ipython 0.11.0 via Anaconda 1.5.0 (64bit) and spyder on Windows 7 (64bit), python version is 2.7.4.
If I have understood you correctly, both from this question as well as your previous one on the same subject, the following should be basic solutions you could customize to your needs.
Several subplots:
Note that this solution will output as many subplots as there are Spectral classes (M0, M1, ...) vertically on the same figure. If you wish to save the plot of each Spectral class in a separate figure, the code needs some modifications.
import pandas as pd
from pandas import DataFrame, read_csv
import numpy as np
import matplotlib.pyplot as plt
# Here you put your code to read the CSV-file into a DataFrame df
plt.figure(figsize=(7,5)) # Set the size of your figure, customize for more subplots
for i in range(len(df)):
xs = np.array(df[df.columns[0::2]])[i] # Use values from odd numbered columns as x-values
ys = np.array(df[df.columns[1::2]])[i] # Use values from even numbered columns as y-values
plt.subplot(len(df), 1, i+1)
plt.plot(xs, ys, marker='o') # Plot circle markers with a line connecting the points
for j in range(len(xs)):
plt.annotate(df.columns[0::2][j][-3:] + '"', # Annotate every plotted point with last three characters of the column-label
xy = (xs[j],ys[j]),
xytext = (0, 5),
textcoords = 'offset points',
va = 'bottom',
ha = 'center',
clip_on = True)
plt.title('Spectral class ' + df.index[i])
plt.xlabel('Limiting Magnitude')
plt.ylabel('Exposure Time')
plt.grid(alpha=0.4)
plt.tight_layout()
plt.show()
All in same Axes, grouped by rows (M0, M1, ...)
Here is another solution to get all the different Spectral classes plotted in the same Axes with a legend identifying the different classes. The plt.yscale('log') is optional, but seeing as how the values span such a great range, it is recommended.
import pandas as pd
from pandas import DataFrame, read_csv
import numpy as np
import matplotlib.pyplot as plt
# Here you put your code to read the CSV-file into a DataFrame df
for i in range(len(df)):
xs = np.array(df[df.columns[0::2]])[i] # Use values from odd numbered columns as x-values
ys = np.array(df[df.columns[1::2]])[i] # Use values from even numbered columns as y-values
plt.plot(xs, ys, marker='o', label=df.index[i])
for j in range(len(xs)):
plt.annotate(df.columns[0::2][j][-3:] + '"', # Annotate every plotted point with last three characters of the column-label
xy = (xs[j],ys[j]),
xytext = (0, 6),
textcoords = 'offset points',
va = 'bottom',
ha = 'center',
rotation = 90,
clip_on = True)
plt.title('Spectral classes')
plt.xlabel('Limiting Magnitude')
plt.ylabel('Exposure Time')
plt.grid(alpha=0.4)
plt.yscale('log')
plt.legend(loc='best', title='Spectral classes')
plt.show()
All in same Axes, grouped by columns (1.3", 2.0", 2.5")
A third solution is as shown below, where the data are grouped by the series (columns 1.3", 2.0", 2.5") rather than by the Spectral class (M0, M1, ...). This example is very similar to
#askewchan's solution. One difference is that the y-axis here is a logarithmic axis, making the lines pretty much parallel.
import pandas as pd
from pandas import DataFrame, read_csv
import numpy as np
import matplotlib.pyplot as plt
# Here you put your code to read the CSV-file into a DataFrame df
xs = np.array(df[df.columns[0::2]]) # Use values from odd numbered columns as x-values
ys = np.array(df[df.columns[1::2]]) # Use values from even numbered columns as y-values
for i in range(df.shape[1]/2):
plt.plot(xs[:,i], ys[:,i], marker='o', label=df.columns[0::2][i][-3:]+'"')
for j in range(len(xs[:,i])):
plt.annotate(df.index[j], # Annotate every plotted point with its Spectral class
xy = (xs[:,i][j],ys[:,i][j]),
xytext = (0, -6),
textcoords = 'offset points',
va = 'top',
ha = 'center',
clip_on = True)
plt.title('Spectral classes')
plt.xlabel('Limiting Magnitude')
plt.ylabel('Exposure Time')
plt.grid(alpha=0.4)
plt.yscale('log')
plt.legend(loc='best', title='Series')
plt.show()
You can call pyplot.plot(time, mag) three different times in the same figure. It would be wise to give a label to them. Something like this:
import matplotlib.pyplot as plt
...
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(df['LimMag1.3'], df['ExpTime1.3'], label="1.3")
ax.plot(df['LimMag2.0'], df['ExpTime2.0'], label="2.0")
ax.plot(df['LimMag2.5'], df['ExpTime2.5'], label="2.5")
plt.show()
If you want to loop it, this would work:
fig = plt.figure()
ax = fig.add_subplot(111)
for x,y in [['LimMag1.3', 'ExpTime1.3'],['LimMag2.0', 'ExpTime2.0'], ['LimMag2.5','ExpTime2.5']]:
ax.plot(df[x], df[y], label=y)
plt.show()