I would be very happy if someone could help me with this:
I created a loop using pandas and plotly express which creates n stacked subplots from a tuple of dataframes selected by the user.
The source data has 10 decimal places, so I set
pd.set_option('precision',10)
The dataframes show adequate decimal precision, the scatter plots work, but I cannot get the hover label to show all 10 decimal places.
I tried to set
fig.update_layout(hoverlabel_namelength=-1)
but it only changes the X-Axis reference in the hoverlabel, not the Y-Axis (containing the numbers).
Can anyone help me?
Thank you very much in advance!!
Maria
Here is my source program:
#import libraries
import tkinter as tk
import tkinter.filedialog
from pathlib import Path
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import numpy as np
pd.set_option('precision',10)
#select files into tuple 'datafiles' via tkinter
root = tkinter.Tk()
pathdir='/***/DSM_Exports/'
datafiles = tkinter.filedialog.askopenfilenames(parent=root,title='Choose a file', initialdir=pathdir)
datafiles = root.tk.splitlist(datafiles)
#prepare subplots template n rows, 1 column
fig = make_subplots(rows=len(datafiles), cols=1, shared_xaxes=True, vertical_spacing=0.01)
# set up loop to create subplot
for counter in range (0, len(datafiles)): #Set up loop with length of datafiles tuple
print(counter, datafiles[counter])
# import file
table=pd.read_csv(datafiles[counter], sep="\t", header=None)
pd.set_option('expand_frame_repr', False)
# extract DSM cumulative dose column
numrows = table.shape[0]+1
print('Number of rows', numrows)
DSMcml= table[[1,2,3]] #extract colulmns start time, end time and cumul dose
#double paranthesis!
DSMcml= DSMcml.iloc[1:numrows] #cut column name
DSMcml[2]= pd.to_datetime(DSMcml[2]) #convert to datetime endtime
DSMcml[3]=DSMcml[3].str.replace(',','.') #change dot to comma in [3]
DSMcml[3]=DSMcml[3].astype(float, errors = 'raise') #change [3] to float
DSMcml= DSMcml[DSMcml[3]>=0].dropna() #>>remove lines with values <0
fig_Xdata= DSMcml[2] #extract end times for X-axis
fig_Ydata= DSMcml[3].round(10) #extract cumul dose for Y-axis
tracename=Path(datafiles[counter]).stem
fig.add_trace(
go.Scatter(x=fig_Xdata, y=fig_Ydata, mode='lines', name=tracename),
row=counter+1, col=1)
fig.update_layout(title_text=datafiles[counter], hovermode='x unified', hoverlabel_namelength=-1)
fig.update_xaxes(showspikes=True, spikecolor='green', spikesnap='cursor', spikemode='across', spikedash='solid')
counterstring=str(counter+1) #set x-axis indicator for shared spike-line
fig.update_traces(xaxis='x'+counterstring) # set shared spike-line
fig.show()
```
You can use a hovertemplate when you add your traces:
fig.add_trace(go.Scatter(x=fig_Xdata, y=fig_Ydata,
hovertemplate='%{y:.10f}', mode='lines', name=tracename), row=counter+1, col=1)
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
My sample data was as follows
Tag_Typ
Alpha_Estimate
Beta_Estimate
PM01_Avg_Cost
PM02_Avg_Cost
OLK-AC-101-14A_PM01
497.665
0.946584
1105.635
462.3833775
OLK-AC-103-01_PM01
288.672
0.882831
1303.8875
478.744375
OLK-AC-1105-01_PM01
164.282
0.787158
763.4475758
512.185814
OLK-AC-236-05A_PM01
567.279
0.756839
640.718
450.3277778
OLK-AC-276-05A_PM01
467.53
0.894773
1536.78625
439.78
This my sample code
import pandas as pd
import numpy as np
from reliability.Repairable_systems import optimal_replacement_time
import matplotlib.pyplot as plt
data = pd.read_excel (r'C:\Users\\EU_1_EQ_PM01_Cost.xlsx')
data_frame = pd.DataFrame(data, columns= ['Alpha_Estimate','Beta_Estimate','PM01_Avg_Cost','PM02_Avg_Cost'])
Alpha_Est=pd.DataFrame(data, columns= ['Alpha_Estimate'])
Beta_Est=pd.DataFrame(data, columns= ['Beta_Estimate'])
PM_Est=pd.DataFrame(data, columns= ['PM02_Avg_Cost'])
CM_Est=pd.DataFrame(data, columns= ['PM01_Avg_Cost'])
optimal_replacement_time(cost_PM=PM_Est, cost_CM=CM_Est, weibull_alpha=Alpha_Est, weibull_beta=Beta_Est,q=0)
plt.show()
I need to loop through the value set for each tag and pass those values to the Optimal replacement function to return the results.
[Sample Output]
ValueError: Can only compare identically-labeled DataFrame objects
I would appreciate any suggestions on how I can pass the values of the PM cost, PPM cost, and the distribution parameters alpha and beta in the function as I iterate through the tag-type and print the results for each tag. Thanks.
The core of your question is how to iterate through a list in Python. This will achieve what you're after:
import pandas as pd
from reliability.Repairable_systems import optimal_replacement_time
df = pd.read_excel(io=r"C:\Users\Matthew Reid\Desktop\sample_data.xlsx")
alpha = df["Alpha_Estimate"].tolist()
beta = df["Beta_Estimate"].tolist()
CM = df["PM01_Avg_Cost"].tolist()
PM = df["PM02_Avg_Cost"].tolist()
ORT = []
for i in range(len(alpha)):
ort = optimal_replacement_time(cost_PM=PM[i], cost_CM=CM[i], weibull_alpha=alpha[i], weibull_beta=beta[i],q=0)
ORT.append(ort.ORT)
print('List of the optimal replacement times:\n',ORT)
On a separate note, all of your beta values are less than 1. This means the hazard rate is decreasing (aka. infant mortality / early life failures). When you run the above script, each iteration will print the warning:
"WARNING: weibull_beta is < 1 so the hazard rate is decreasing, therefore preventative maintenance should not be conducted."
If you have any further questions, you know how to contact me :)
I want to dynamically write and display HTML with a code cell in Jupyter Notebook. The objective is to generate the HTML to display table, div, img tags in some way I choose. I want to capture img data and place it where I want in this auto generated HTML.
So far I've figured out that I can do the following:
from IPython.core.display import HTML
HTML("<h1>Hello</h1>")
and get:
Hello
That's great. However, I want to be able to do this:
HTML("<h1>Hello</h1><hr/><img src='somestring'/>")
and get something similar to a Hello with a horizontal line and an image below it, where the image is the same one as below.
import pandas as pd
import numpy as np
np.random.seed(314)
df = pd.DataFrame(np.random.randn(1000, 2), columns=['x', 'y'])
df.plot.scatter(0, 1)
The result should look like this:
Question
What do I replace 'something' with in order to implement this? And more to the point, how do I get it via python?
I would have imagined there was an attribute on a figure object that would hold an serialized version of the image but I can't find it.
After some digging around. Credit to Dmitry B. for pointing me in the right direction.
Solution
from IPython.core.display import HTML
import binascii
from StringIO import StringIO
import matplotlib.pyplot as plt
# open IO object
sio = StringIO()
# generate random DataFrame
np.random.seed(314)
df = pd.DataFrame(np.random.randn(1000, 2), columns=['x', 'y'])
# initialize figure and axis
fig, ax = plt.subplots(1, 1)
# plot DataFrame
ax.scatter(df.iloc[:, 0], df.iloc[:, 1]);
# print raw canvas data to IO object
fig.canvas.print_png(sio)
# convert raw binary data to base64
# I use this to embed in an img tag
img_data = binascii.b2a_base64(sio.getvalue())
# keep img tag outter html in its own variable
img_html = '<img src="data:image/png;base64,{}
">'.format(img_data)
HTML("<h1>Hello</h1><hr/>"+img_html)
I end up with:
from IPython.core.display import Image
import io
s = io.BytesIO()
# make your figure here
plt.savefig(s, format='png', bbox_inches="tight")
plt.close()
Image(s.getvalue())
Let say you have base64 encoded image data:
img_data =
"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"
then in have it rendered inside of an iPython cell you simply do:
from IPython.core.display import Image
Image(data=img_data)
I'm going to build on what was answered by others (piRSquared) because it didn't work for me with Jupyter and Python 3. I wrote the following function, which will take any plot function I define and call it, and capture the outputs without displaying them in Jupyter. I personally use this in to build custom HTML machine learning reports based on many model iterations I execute using Livy and Spark.
from IPython.core.display import HTML
import binascii
from io import BytesIO
import matplotlib.pyplot as plt
import numpy as np
import base64
def capturePlotHTML(plotFunction):
# open IO object
sio3 = BytesIO()
plotFunction()
plt.savefig(sio3)
sio3.seek(0)
data_uri = base64.b64encode(sio3.read()).decode('ascii')
html_out = '<html><head></head><body>'
html_out += '<img src="data:image/png;base64,{0}" align="left">'.format(data_uri)
html_out += '</body></html>'
#prevents plot from showing in output
plt.close()
return (HTML(html_out))
# Plot Wrappers
# Advanced Wrapper for more complex visualizations (seaborn, etc)
class plotRegline:
def __init__(self):
#// could also pass in name as arg like this #def __init__(self, name):
reg_line_prepped_pdf = pandas_input_pdf
sns.lmplot(x='predicted',y='actual',data=reg_line_prepped_pdf,fit_reg=True, height=3, aspect=2).fig.suptitle("Regression Line")
# Basic Wrapper for simple matplotlib visualizations
def plotTsPred():
ts_plot_prepped_pdf = pandas_input_pdf
ts_plot_prepped_pdf.index = pd.to_datetime(ts_plot_prepped_pdf.DAYDATECOLUMN)
ts_plot_prepped_pdf = ts_plot_prepped_pdf.drop(columns=["DAYDATECOLUMN"])
ts_plot_prepped_pdf.plot(title="Predicted Vs Actual -- Timeseries Plot -- Days", figsize=(25,6))
#building the plots and capturing the outputs
regline_html = capturePlotHTML(plotRegline)
ts_plot_day_html = capturePlotHTML(plotTsPred)
# could be any list number of html objects
html_plots = [regline_html, ts_plot_day_html]
combined_html_plots = display_html(*html_plots)
# the following can be run in this code block or another display the results
combined_html_plotes
The answer by piRSquared no longer works with Python 3. I had to change it to:
from IPython.core.display import HTML
import binascii
from io import BytesIO
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
# open IO object
bio = BytesIO()
# generate random DataFrame
np.random.seed(314)
df = pd.DataFrame(np.random.randn(1000, 2), columns=['x', 'y'])
# initialize figure and axis
fig, ax = plt.subplots(1, 1);
# plot DataFrame
ax.scatter(df.iloc[:, 0], df.iloc[:, 1]);
# print raw canvas data to IO object
fig.canvas.print_png(bio)
plt.close(fig)
# convert raw binary data to base64
# I use this to embed in an img tag
img_data = binascii.b2a_base64(bio.getvalue()).decode()
# keep img tag outter html in its own variable
img_html = '<img src="data:image/png;base64,{}
">'.format(img_data)
HTML("<h1>Hello</h1><hr/>"+img_html)
Specifically, I import from io, not StringIO, and I use BytesIO rather than StringIO. I needed to decode the bytes into a string for inserting into the HTML. I also added the required imports of numpy and pandas for the example plot to work, and added plt.close(fig) so that you don't end up with two figures in the output.
If you want to show the results of DataFrame.plot in an iPython cell, try this:
import pandas as pd
import numpy as np
%matplotlib inline
np.random.seed(314)
df = pd.DataFrame(np.random.randn(1000, 2), columns=['x', 'y'])
df.plot.scatter(0, 1)
I would like create a daily candlestick plot from data i downloaded from yahoo using pandas. I'm having trouble figuring out how to use the candlestick matplotlib function in this context.
Here is the code:
#The following example, downloads stock data from Yahoo and plots it.
from pandas.io.data import get_data_yahoo
import matplotlib.pyplot as plt
from matplotlib.pyplot import subplots, draw
from matplotlib.finance import candlestick
symbol = "GOOG"
data = get_data_yahoo(symbol, start = '2013-9-01', end = '2013-10-23')[['Open','Close','High','Low','Volume']]
ax = subplots()
candlestick(ax,data['Open'],data['High'],data['Low'],data['Close'])
Thanks
Andrew.
Using bokeh:
import io
from math import pi
import pandas as pd
from bokeh.plotting import figure, show, output_file
df = pd.read_csv(
io.BytesIO(
b'''Date,Open,High,Low,Close
2016-06-01,69.6,70.2,69.44,69.76
2016-06-02,70.0,70.15,69.45,69.54
2016-06-03,69.51,70.48,68.62,68.91
2016-06-04,69.51,70.48,68.62,68.91
2016-06-05,69.51,70.48,68.62,68.91
2016-06-06,70.49,71.44,69.84,70.11
2016-06-07,70.11,70.11,68.0,68.35'''
)
)
df["Date"] = pd.to_datetime(df["Date"])
inc = df.Close > df.Open
dec = df.Open > df.Close
w = 12*60*60*1000
TOOLS = "pan,wheel_zoom,box_zoom,reset,save"
p = figure(x_axis_type="datetime", tools=TOOLS, plot_width=1000, title
= "Candlestick")
p.xaxis.major_label_orientation = pi/4
p.grid.grid_line_alpha=0.3
p.segment(df.Date, df.High, df.Date, df.Low, color="black")
p.vbar(df.Date[inc], w, df.Open[inc], df.Close[inc], fill_color="#D5E1DD", line_color="black")
p.vbar(df.Date[dec], w, df.Open[dec], df.Close[dec], fill_color="#F2583E", line_color="black")
output_file("candlestick.html", title="candlestick.py example")
show(p)
Code above forked from here:
http://docs.bokeh.org/en/latest/docs/gallery/candlestick.html
I have no reputation to comment #randall-goodwin answer, but for pandas 0.16.2 line:
# convert the datetime64 column in the dataframe to 'float days'
data.Date = mdates.date2num(data.Date)
must be:
data.Date = mdates.date2num(data.Date.dt.to_pydatetime())
because matplotlib does not support the numpy datetime64 dtype
I stumbled across a great pastebin entry: http://pastebin.com/ne7Fjdiq that does this well. I too was having trouble getting the calling syntax right. It usually revolves around transforming your data in simple ways to get the function to work right. My issue was with the datetime. There must be something in my format data. Once I replaced the Date series with range(maxdata) then it worked.
data = pandas.read_csv('data.csv', parse_dates={'Timestamp': ['Date', 'Time']}, index_col='Timestamp')
ticks = data.ix[:, ['Price', 'Volume']]
bars = ticks.Price.resample('1min', how='ohlc')
barsa = bars.fillna(method='ffill')
fig = plt.figure()
fig.subplots_adjust(bottom=0.1)
ax = fig.add_subplot(111)
plt.title("Candlestick chart")
volume = ticks.Volume.resample('1min', how='sum')
value = ticks.prod(axis=1).resample('1min', how='sum')
vwap = value / volume
Date = range(len(barsa))
#Date = matplotlib.dates.date2num(barsa.index)#
DOCHLV = zip(Date , barsa.open, barsa.close, barsa.high, barsa.low, volume)
matplotlib.finance.candlestick(ax, DOCHLV, width=0.6, colorup='g', colordown='r', alpha=1.0)
plt.show()
Here is the solution:
from pandas.io.data import get_data_yahoo
import matplotlib.pyplot as plt
from matplotlib import dates as mdates
from matplotlib import ticker as mticker
from matplotlib.finance import candlestick_ohlc
import datetime as dt
symbol = "GOOG"
data = get_data_yahoo(symbol, start = '2014-9-01', end = '2015-10-23')
data.reset_index(inplace=True)
data['Date']=mdates.date2num(data['Date'].astype(dt.date))
fig = plt.figure()
ax1 = plt.subplot2grid((1,1),(0,0))
plt.ylabel('Price')
ax1.xaxis.set_major_locator(mticker.MaxNLocator(6))
ax1.xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m-%d'))
candlestick_ohlc(ax1,data.values,width=0.2)
Found this question when I too was looking how to use candlestick with a pandas dataframe returned from one of the DataReader services like get_data_yahoo. I eventually figured it out. One of the keys was this other question, answered by Wes McKinney and RJRyV. Here is that link:
Pandas convert dataframe to array of tuples
The key was to read the candlestick.py function definition to determine how it expected to receive the data. The date needed to be converted first, then the entire dataframe needed to be converted to an array of tuples.
Here is the final code that worked for me. Maybe there is some other Candlestick chart out there somewhere that works directly on a pandas dataframe returned from one of the stock quote services. That would be very nice.
# Imports
from pandas.io.data import get_data_yahoo
from datetime import datetime, timedelta
import matplotlib.dates as mdates
from matplotlib.pyplot import subplots, draw
from matplotlib.finance import candlestick
import matplotlib.pyplot as plt
# get the data on a symbol (gets last 1 year)
symbol = "TSLA"
data = get_data_yahoo(symbol, datetime.now() - timedelta(days=365))
# drop the date index from the dateframe
data.reset_index(inplace = True)
# convert the datetime64 column in the dataframe to 'float days'
data.Date = mdates.date2num(data.Date)
# make an array of tuples in the specific order needed
dataAr = [tuple(x) for x in data[['Date', 'Open', 'Close', 'High', 'Low']].to_records(index=False)]
# construct and show the plot
fig = plt.figure()
ax1 = plt.subplot(1,1,1)
candlestick(ax1, dataAr)
plt.show()
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()