So currently learning how to import data and work with it in matplotlib and I am having trouble even tho I have the exact code from the book.
This is what the plot looks like, but my question is how can I get it where there is no white space between the start and the end of the x-axis.
Here is the code:
import csv
from matplotlib import pyplot as plt
from datetime import datetime
# Get dates and high temperatures from file.
filename = 'sitka_weather_07-2014.csv'
with open(filename) as f:
reader = csv.reader(f)
header_row = next(reader)
#for index, column_header in enumerate(header_row):
#print(index, column_header)
dates, highs = [], []
for row in reader:
current_date = datetime.strptime(row[0], "%Y-%m-%d")
dates.append(current_date)
high = int(row[1])
highs.append(high)
# Plot data.
fig = plt.figure(dpi=128, figsize=(10,6))
plt.plot(dates, highs, c='red')
# Format plot.
plt.title("Daily high temperatures, July 2014", fontsize=24)
plt.xlabel('', fontsize=16)
fig.autofmt_xdate()
plt.ylabel("Temperature (F)", fontsize=16)
plt.tick_params(axis='both', which='major', labelsize=16)
plt.show()
There is an automatic margin set at the edges, which ensures the data to be nicely fitting within the axis spines. In this case such a margin is probably desired on the y axis. By default it is set to 0.05 in units of axis span.
To set the margin to 0 on the x axis, use
plt.margins(x=0)
or
ax.margins(x=0)
depending on the context. Also see the documentation.
In case you want to get rid of the margin in the whole script, you can use
plt.rcParams['axes.xmargin'] = 0
at the beginning of your script (same for y of course). If you want to get rid of the margin entirely and forever, you might want to change the according line in the matplotlib rc file:
axes.xmargin : 0
axes.ymargin : 0
Example
import seaborn as sns
import matplotlib.pyplot as plt
tips = sns.load_dataset('tips')
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 4))
tips.plot(ax=ax1, title='Default Margin')
tips.plot(ax=ax2, title='Margins: x=0')
ax2.margins(x=0)
Alternatively, use plt.xlim(..) or ax.set_xlim(..) to manually set the limits of the axes such that there is no white space left.
If you only want to remove the margin on one side but not the other, e.g. remove the margin from the right but not from the left, you can use set_xlim() on a matplotlib axes object.
import seaborn as sns
import matplotlib.pyplot as plt
import math
max_x_value = 100
x_values = [i for i in range (1, max_x_value + 1)]
y_values = [math.log(i) for i in x_values]
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 4))
sn.lineplot(ax=ax1, x=x_values, y=y_values)
sn.lineplot(ax=ax2, x=x_values, y=y_values)
ax2.set_xlim(-5, max_x_value) # tune the -5 to your needs
Related
So currently learning how to import data and work with it in matplotlib and I am having trouble even tho I have the exact code from the book.
This is what the plot looks like, but my question is how can I get it where there is no white space between the start and the end of the x-axis.
Here is the code:
import csv
from matplotlib import pyplot as plt
from datetime import datetime
# Get dates and high temperatures from file.
filename = 'sitka_weather_07-2014.csv'
with open(filename) as f:
reader = csv.reader(f)
header_row = next(reader)
#for index, column_header in enumerate(header_row):
#print(index, column_header)
dates, highs = [], []
for row in reader:
current_date = datetime.strptime(row[0], "%Y-%m-%d")
dates.append(current_date)
high = int(row[1])
highs.append(high)
# Plot data.
fig = plt.figure(dpi=128, figsize=(10,6))
plt.plot(dates, highs, c='red')
# Format plot.
plt.title("Daily high temperatures, July 2014", fontsize=24)
plt.xlabel('', fontsize=16)
fig.autofmt_xdate()
plt.ylabel("Temperature (F)", fontsize=16)
plt.tick_params(axis='both', which='major', labelsize=16)
plt.show()
There is an automatic margin set at the edges, which ensures the data to be nicely fitting within the axis spines. In this case such a margin is probably desired on the y axis. By default it is set to 0.05 in units of axis span.
To set the margin to 0 on the x axis, use
plt.margins(x=0)
or
ax.margins(x=0)
depending on the context. Also see the documentation.
In case you want to get rid of the margin in the whole script, you can use
plt.rcParams['axes.xmargin'] = 0
at the beginning of your script (same for y of course). If you want to get rid of the margin entirely and forever, you might want to change the according line in the matplotlib rc file:
axes.xmargin : 0
axes.ymargin : 0
Example
import seaborn as sns
import matplotlib.pyplot as plt
tips = sns.load_dataset('tips')
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 4))
tips.plot(ax=ax1, title='Default Margin')
tips.plot(ax=ax2, title='Margins: x=0')
ax2.margins(x=0)
Alternatively, use plt.xlim(..) or ax.set_xlim(..) to manually set the limits of the axes such that there is no white space left.
If you only want to remove the margin on one side but not the other, e.g. remove the margin from the right but not from the left, you can use set_xlim() on a matplotlib axes object.
import seaborn as sns
import matplotlib.pyplot as plt
import math
max_x_value = 100
x_values = [i for i in range (1, max_x_value + 1)]
y_values = [math.log(i) for i in x_values]
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 4))
sn.lineplot(ax=ax1, x=x_values, y=y_values)
sn.lineplot(ax=ax2, x=x_values, y=y_values)
ax2.set_xlim(-5, max_x_value) # tune the -5 to your needs
I am looking to change the colors of my bar graph based on if there are any negative values. I want positive values to be crimson and negative values to be deepskyblue. I can't seem to find the best method of accomplishing this.
What my figure looks like before I tried making changes: Link to figure
Below are segments of my code, with the last four lines being the problem (TypeError: '>=' not supported between instances of 'list' and 'int':
filename='2015_tAnoms.csv'
lat = []
tAnom = []
with open(filename,'r') as csvfile:
points = csv.reader(csvfile, delimiter=',')
next(points)
for row in points:
lat.append(int(row[0]))
tAnom.append(Decimal(row[1]))
import matplotlib.pyplot as plt
from matplotlib.pyplot import figure
import numpy as np
figure(num=None, figsize=(8, 6), dpi=300, facecolor='w', edgecolor='k')
axes = plt.gca()
axes.grid(color='lightgray', alpha=0.6, which='major', axis='y', linestyle='-')
axes.set_facecolor((0,0,0))
axes.set_xlim([-90,90])
axes.set_ylim([-1,3])
lat = np.array(lat)
tAnom = np.array(tAnom)
posValues = tAnom >= 0
negValues = tAnom < 0
plt.bar(lat[posValues],tAnom[posValues],color='crimson')
plt.bar(lat[negValues],tAnom[negValues],color='deepskyblue')
Image with correct coloring, but squished data
I'm am running a fundamental economic analysis and when I get to visualising and charting I am not able to align the dates with the graph.
I wanted the most recent date entry to show on the right and the rest of the dates to show every two years.
I have tried literally everything and cant find the solution.
Here is my code:
%matplotlib inline
import pandas as pd
from matplotlib import pyplot
import matplotlib.dates as mdates
df = pd.read_csv('https://fred.stlouisfed.org/graph/fredgraph.csvbgcolor=%23e1e9f0&chart_type=line&drp=0&fo=open%20sans&graph_bgcolor=%23ffffff&height=450&mode=fred&recession_bars=off&txtcolor=%23444444&ts=12&tts=12&width=1168&nt=0&thu=0&trc=0&show_legend=yes&show_axis_titles=yes&show_tooltip=yes&id=NAEXKP01EZQ657S&scale=left&cosd=1995-04-01&coed=2020-04-01&line_color=%234572a7&link_values=false&line_style=solid&mark_type=none&mw=3&lw=2&ost=-99999&oet=99999&mma=0&fml=a&fq=Quarterly&fam=avg&fgst=lin&fgsnd=2020-02-01&line_index=1&transformation=lin&vintage_date=2020-09-21&revision_date=2020-09-21&nd=1995-04-01')
df = df.set_index('DATE')
df['12MonthAvg'] = df.rolling(window=12).mean().dropna(how='all')
df['9MonthAvg'] = df['12MonthAvg'].rolling(window=12).mean().dropna(how='all')
df['Spread'] = df['12MonthAvg'] - df['9MonthAvg']
pyplot.style.use("seaborn")
pyplot.subplots(figsize=(10, 5), dpi=85)
df['Spread'].plot().set_title('EUROPE: GDP Q Growth Rate (12M/12M Avg Spread)', fontsize=16)
df['Spread'].plot().axhline(0, linestyle='-', color='r',alpha=1, linewidth=2, marker='')
df['Spread'].plot().spines['left'].set_position(('outward', 10))
df['Spread'].plot().spines['bottom'].set_position(('outward', 10))
df['Spread'].plot().spines['right'].set_visible(False)
df['Spread'].plot().spines['top'].set_visible(False)
df['Spread'].plot().yaxis.set_ticks_position('left')
df['Spread'].plot().xaxis.set_ticks_position('bottom')
df['Spread'].plot().text(0.50, 0.02, "Crossing red line downwards / Crossing red line Upwards",
transform=pyplot.gca().transAxes, fontsize=14, ha='center', color='blue')
df['Spread'].plot().fmt_xdata = mdates.DateFormatter('%Y-%m-%d')
print(df['Spread'].tail(3))
pyplot.autoscale()
pyplot.show()
And the output:
This is the raw data:
There is a couple of corrections to your code.
In your URL insert "?" after fredgraph.csv. It starts so called query string,
where bgcolor is the first parameter.
Read your DataFrame with additional parameters:
df = pd.read_csv('...', parse_dates=[0], index_col=[0])
The aim is to:
read Date column as datetime,
set it as the index.
Create additional columns as:
df['12MonthAvg'] = df.NAEXKP01EZQ657S.rolling(window=12).mean()
df['9MonthAvg'] = df.NAEXKP01EZQ657S.rolling(window=9).mean()
df['Spread'] = df['12MonthAvg'] - df['9MonthAvg']
Corrections:
9MonthAvg (as I think) should be computed from the source column,
not from 12MonthAvg,
dropna here is not needed, as you create whole column anyway.
Now is the place to use dropna() on Spread column and save it in
a dedicated variable:
spread = df['Spread'].dropna()
Draw your figure the following way:
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
plt.style.use("seaborn")
fig, ax = plt.subplots(figsize=(10, 5), dpi=85)
plt.plot_date(spread.index, spread, fmt='-')
ax.set_title('EUROPE: GDP Q Growth Rate (12M/12M Avg Spread)', fontsize=16)
ax.axhline(0, linestyle='-', color='r',alpha=1, linewidth=2, marker='')
ax.spines['left'].set_position(('outward', 10))
ax.spines['bottom'].set_position(('outward', 10))
ax.spines['right'].set_visible(False)
ax.spines['top'].set_visible(False)
ax.text(0.50, 0.02, "Crossing red line downwards / Crossing red line Upwards",
transform=ax.transAxes, fontsize=14, ha='center', color='blue')
ax.xaxis.set_major_formatter(mdates.DateFormatter(fmt='%Y-%m-%d'))
plt.show()
Corrections:
plt.subplots returns fig and ax, so I saved them (actually, only ax
is needed).
When one axis contains dates, it is better to use plot_date.
I changed the way DateFormatter is set.
Using the above code I got the following picture:
I am trying to produce a subplot, plotting 3 time series over 2 different axes.
My time series go from Jan-2007 till Sep-2017 (one data point per month).
My problem is that I cannot change the limits of the x axis.
I have tried both xlim and set_xlim, but they have no effect whatsoever.
What am I doing wrong?
An example of my code is below.
import numpy as np
import pandas as pd
import datetime as dt
import dateutil
import matplotlib.pyplot as plt
import matplotlib
import matplotlib.ticker as mtick
mystart = dt.date(2007,1,1)
mydates =[mystart]
for i in np.arange(1,130):
mydates.append( mystart +dateutil.relativedelta.relativedelta(months=i))
df=pd.DataFrame()
df['month']=mydates
df['a']= np.arange(1,131)
df['b']=df['a']/2
df['c']=0.25
fig,ax=plt.subplots(2)
ax[0].set_title('My title')
l1 = ax[0].plot_date( df['month'],df['a'], label= 'a (left axis)', color='blue', ls='solid', marker ='')
l2 = ax[0].plot_date( df['month'],df['b'], label= 'b (left axis)',color='red', ls='solid', marker ='')
# THESE BELOW ARE THE TWO LINES I CANNOT GET TO WORK!!!
#plt.xlim(xmin= dt.date(2012,1,31),xmax=dt.date(2017,9,30))
ax[0].set_xlim([dt.date(2012,1,31),dt.date(2017,9,30)], auto=True)
ax[0].grid()
ax2=ax[0].twinx()
l3 = ax2.plot_date( df['month'],df['c']*100 , label= 'some % (right axis)', color='green', ls='solid', marker ='')
fmt = '%.2f%%' # Format you want the ticks, e.g. '40%'
yticks = mtick.FormatStrFormatter(fmt)
ax2.yaxis.set_major_formatter(yticks)
ls=l1+l2+l3
labs=[l.get_label() for l in ls]
ax[0].legend(ls, labs, loc='upper left')
ax[1].set_title('Something else will go here...')
plt.show()
Set the limits of the axes after you have created the twin axes and plotted to it.
ax2=ax[0].twinx()
l3 = ax2.plot_date( ... )
ax[0].set_xlim( ... )
I got it: the issue is the secondary axis.
I must repeat set_xlim for ax2, as well:
ax2.set_xlim([dt.datetime(2012,1,31),dt.datetime(2017,9,30)], auto=True)
I am not sure if this is a bug, TBH. I would have expected that creating a twin axis would have replicated the same xlim.
This is my first time asking a Python question online. I have always been able to find answers to my questions on this site..until now. I am trying to plot data that were developed using the Index Sequential Method, which is a technique for projecting historical data into the future. I have 105 charts that each cover 47 years of data. The first chart x-axis ranges from 1906-1952, the second 1907-1953, thir 1908-1954, etc. My problem is when I get to 1963, which is when the 47th year reverts back to the begining (1906). So the 1963 chart xaxis would look like this: 1963, 1964, 1965,...2008,2009,2010,1906. The 1964 chart xaxis would look like this: 1964, 1965, 1967,...2009, 2010, 1906, 1907.
I can get the data to plot fine, I just need help figuring out how to format the xaxis to accept the unique wrap-around situation when it occurs.
There are three charts per page (ax1, ax2, and ax3). yearList and chartList are the x and y data, respectively. The code below is part of a for loop that creates the yearList and chartList data sets, and it creates the charts with the wrong xaxis labels.
import matplotlib, pyPdf
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import matplotlib.ticker as tkr
from matplotlib.ticker import MultipleLocator
import matplotlib.figure as figure
plt.rcParams['font.family'] = 'Times New Roman'
locator = mdates.YearLocator(2)
minorLocator = MultipleLocator(1)
dateFmt = mdates.DateFormatter('%Y')
datemin = min(yearList)
datemax = max(yearList)
fig, (ax1, ax2, ax3) = plt.subplots(3,1,sharex=False)
#3X3 Top to bottom
ax1.bar(yearList1, chartList1, width=200, align='center')
ax2.bar(yearList2, chartList2, width=200, align='center')
ax3.bar(yearList3, chartList3, width=200, align='center')
axList = [ax1, ax2, ax3]
for ax in axList:
ax.xaxis.set_major_locator(locator)
ax.xaxis.set_major_formatter(dateFmt)
ax.xaxis.set_minor_locator(minorLocator)
ax.set_xlim(datemin - timedelta(365), datemax + timedelta(365))
ax.grid(1)
ax.set_ylim(0,30)
ax.set_yticks(np.arange(0, 31, 5))
ax.yaxis.set_minor_locator(minorLocator)
#Rotate tick labels 90 degrees
xlabels = ax.get_xticklabels()
for label in xlabels:
label.set_rotation(90)
fig.tight_layout()
plt.subplots_adjust(right=0.925)
plt.savefig('%s\\run.pdf' % outDir)
You are making a bar graph, which means the x-posistion has little to no meaning aside from the labels, so don't try to plot the bars vs their date, plot them against the integers, and then label them as you wish:
from itertools import izip
fig, axeses = plt.subplots(3,1,sharex=False)
#3X3 Top to bottom
for yl, cl, ax in izip([yearList1, yearList2, yearList3],
[chartList1, chartList2, chartist3],
axeses):
ax.bar(range(len(cl)), cl, align='center')
ax.set_ylim(0,30)
ax.set_yticks(np.arange(0, 31, 5))
ax.yaxis.set_minor_locator(minorLocator)
xlabels = [dateFmt(xl) for xl in yl] # make a list of formatted labels
ax.set_xticks(range(len(cl))) # put the tick markers under your bars
ax.set_xticklabels(xlabels) # set the labels to be your formatted years
#Rotate tick labels 90 degrees
for label in ax.get_xticklabels():
label.set_rotation(90)
# you only need to do this once
fig.tight_layout()
fig.subplots_adjust(right=0.925)
fig.savefig('%s\\run.pdf' % outDir)
Also see the demo and the docs set_xticks and set_xticklabels
You can use the ax.set_ticklabels() function to set the labels.
Example:
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.plot([1, 2, 3, 4], [10, 20, 25, 30])
ax.xaxis.set_ticklabels(["foo" , "bar", "ouch"])
plt.show()
So, just add the transformation that you need, and create the labels list.
maybe something like this:
range = 47
yearList = [1967, 1968,..., last year]
range_of_years = map(lambda x: range(year,year + range), yearList)
for i in range(len(axis_list)):
axis_list[i].xaxis.set_ticklabels(years_list[i])