Develop Reference

How to specify the years on an axis when using plot() on DateTime objects

The plotting goes like this:
plt.plot(df['Date'], df['Price'])
df['Date'] consists of DateTime objects with several years and df['Price'] are integers.
However on the actual line graph, it automatically selects about 4 years spaced apart in the graph with large intervals:
How do I make it so that I can specify the number of years to show on the X axis? Or perhaps show all the years (year only)?
Example:
import pandas as pd
import datetime
import random
dates = []
prices = []
for count in range(10000):
prices.append(random.randint(0, 10))
dates.append(datetime.datetime(random.randint(1960, 2022), random.randint(1, 12), random.randint(1, 27)).strftime("%Y-%m-%d"))
data = {
'Date': dates,
'Price': prices
}
df = pd.DataFrame(data)
df = df.sort_values(by=['Date'], ignore_index = True)
df_temp = df.copy()
df_temp['Date DT'] = pd.to_datetime(df_temp['Date'])
df_temp = df_temp.drop(axis = 'columns', columns = 'Date')
df = df_temp
df
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.pyplot import figure
plt.figure(figsize=(15, 5), dpi = 1000)
plt.plot(df['Date DT'], df['Price'])
# Labels
plt.xlabel('Dates', fontsize = 8)
plt.ylabel('Prices', fontsize = 8)
# Save
plt.title('Example', fontsize = 15)
plt.savefig('example.png', bbox_inches = 'tight')

You can use the xticks function to set the tick marks and labels on the x-axis.
Like This:
plt.plot(df['Date'], df['Price'])
years = [date.year for date in df['Date']]
plt.xticks(df['Date'], years, rotation=45)
plt.show()
EDIT: to only display one unique year each out of years:
import numpy as np
plt.plot(df['Date'], df['Price'])
# Extract the unique years from the 'Date' column
years = np.unique([date.year for date in df['Date']])
# Set the tick marks on the x-axis
plt.xticks(df['Date'], rotation=45)
# Set the labels of the tick marks on the x-axis
plt.gca().set_xticklabels(years)
plt.show()

Printing months in the x axis with pyplot

Data I'm working with: https://drive.google.com/file/d/1xb7icmocz-SD2Rkq4ykTZowxW0uFFhBl/view?usp=sharing
Hey everyone,
I am a bit stuck with editing a plot.
Basically, I would like my x value to display the months in the year, but it doesn't seem to work because of the data type (?). Do you have any idea how I could get my plot to have months in the x axis?
If you need more context about the data, please let me know!!!
Thank you!
Here's my code for the plot and the initial data modifications:
import matplotlib.pyplot as plt
import mplleaflet
import pandas as pd
import matplotlib.dates as mdates
from matplotlib.dates import DateFormatter
import numpy as np
df = pd.read_csv("data/C2A2_data/BinnedCsvs_d400/fb441e62df2d58994928907a91895ec62c2c42e6cd075c2700843b89.csv")
df['degrees']=df['Data_Value']/10
df['Date'] = pd.to_datetime(df['Date'])
df2 = df[df['Date']<'2015-01-01']
df3 = df[df['Date']>='2015-01-01']
max_temp = df2.groupby([(df2.Date.dt.month),(df2.Date.dt.day)])['degrees'].max()
min_temp = df2.groupby([(df2.Date.dt.month),(df2.Date.dt.day)])['degrees'].min()
max_temp2 = df3.groupby([(df3.Date.dt.month),(df3.Date.dt.day)])['degrees'].max()
min_temp2 = df3.groupby([(df3.Date.dt.month),(df3.Date.dt.day)])['degrees'].min()
max_temp.plot(x ='Date', y='degrees', kind = 'line')
min_temp.plot(x ='Date',y='degrees', kind= 'line')
plt.fill_between(range(len(min_temp)),min_temp, max_temp, color='C0', alpha=0.2)
ax = plt.gca()
ax.set(xlabel="Date",
ylabel="Temperature",
title="Extreme Weather in 2015")
plt.legend()
plt.tight_layout()
x = plt.gca().xaxis
for item in x.get_ticklabels():
item.set_rotation(45)
plt.show()
Plot I'm getting:

Option 1 (Most Similar Approach)
Change the index based on month abbreviations using Index.map and calendar
This is just for df2:
import calendar
import matplotlib.pyplot as plt
import pandas as pd
df = pd.read_csv("...")
df['degrees'] = df['Data_Value'] / 10
df['Date'] = pd.to_datetime(df['Date'])
df2 = df[df['Date'] < '2015-01-01']
max_temp = df2.groupby([df2.Date.dt.month, df2.Date.dt.day])['degrees'].max()
min_temp = df2.groupby([df2.Date.dt.month, df2.Date.dt.day])['degrees'].min()
# Update the index to be the desired display format for x-axis
max_temp.index = max_temp.index.map(lambda x: f'{calendar.month_abbr[x[0]]}')
min_temp.index = min_temp.index.map(lambda x: f'{calendar.month_abbr[x[0]]}')
max_temp.plot(x='Date', y='degrees', kind='line')
min_temp.plot(x='Date', y='degrees', kind='line')
plt.fill_between(range(len(min_temp)), min_temp, max_temp,
color='C0', alpha=0.2)
ax = plt.gca()
ax.set(xlabel="Date", ylabel="Temperature", title="Extreme Weather 2005-2014")
x = plt.gca().xaxis
for item in x.get_ticklabels():
item.set_rotation(45)
plt.margins(x=0)
plt.legend()
plt.tight_layout()
plt.show()
As an aside: the title "Extreme Weather in 2015" is incorrect because this data includes all years before 2015. This is "Extreme Weather 2005-2014"
The year range can be checked with min and max as well:
print(df2.Date.dt.year.min(), '-', df2.Date.dt.year.max())
# 2005 - 2014
The title could be programmatically generated with:
title=f"Extreme Weather {df2.Date.dt.year.min()}-{df2.Date.dt.year.max()}"
Option 2 (Simplifying groupby step)
Simplify the code using groupby aggregate to create a single DataFrame then convert the index in the same way as above:
import calendar
import matplotlib.pyplot as plt
import pandas as pd
df = pd.read_csv("...")
df['degrees'] = df['Data_Value'] / 10
df['Date'] = pd.to_datetime(df['Date'])
df2 = df[df['Date'] < '2015-01-01']
# Get Max and Min Degrees in Single Groupby
df2_temp = (
df2.groupby([df2.Date.dt.month, df2.Date.dt.day])['degrees']
.agg(['max', 'min'])
)
# Convert Index to whatever display format is desired:
df2_temp.index = df2_temp.index.map(lambda x: f'{calendar.month_abbr[x[0]]}')
# Plot
ax = df2_temp.plot(
kind='line', rot=45,
xlabel="Date", ylabel="Temperature",
title=f"Extreme Weather {df2.Date.dt.year.min()}-{df2.Date.dt.year.max()}"
)
# Fill between
plt.fill_between(range(len(df2_temp)), df2_temp['min'], df2_temp['max'],
color='C0', alpha=0.2)
plt.margins(x=0)
plt.tight_layout()
plt.show()
Option 3 (Best overall functionality)
Convert the index to a datetime using pd.to_datetime. Choose any leap year to uniform the data (it must be a leap year so Feb-29 does not raise an error). Then set the set_major_formatter using the format string %b to use the month abbreviation:
import matplotlib.dates as mdates
import matplotlib.pyplot as plt
import pandas as pd
df = pd.read_csv("...")
df['degrees'] = df['Data_Value'] / 10
df['Date'] = pd.to_datetime(df['Date'])
df2 = df[df['Date'] < '2015-01-01']
# Get Max and Min Degrees in Single Groupby
df2_temp = (
df2.groupby([df2.Date.dt.month, df2.Date.dt.day])['degrees']
.agg(['max', 'min'])
)
# Convert to DateTime of Same Year
# (Must be a leap year so Feb-29 doesn't raise an error)
df2_temp.index = pd.to_datetime(
'2000-' + df2_temp.index.map(lambda s: '-'.join(map(str, s)))
)
# Plot
ax = df2_temp.plot(
kind='line', rot=45,
xlabel="Date", ylabel="Temperature",
title=f"Extreme Weather {df2.Date.dt.year.min()}-{df2.Date.dt.year.max()}"
)
# Fill between
plt.fill_between(df2_temp.index, df2_temp['min'], df2_temp['max'],
color='C0', alpha=0.2)
# Set xaxis formatter to month abbr with the %b format string
ax.xaxis.set_major_formatter(mdates.DateFormatter('%b'))
plt.tight_layout()
plt.show()
The benefit of this approach is that the index is a datetime and therefore will format better than the string representations of options 1 and 2.

How to get only Adjusted Close Price from Yahoo Finance library

I am using the Yahoo Finance Library in Python to pull data of a stock.
import yahoo_finance
ticker = 'GLD'
begdate = '2014-11-11'
enddate = '2016-11-11'
data = yahoo_finance.Share('GLD')
data1 = data.get_historical(begdate,enddate)
gld_df = pd.DataFrame(data1)
date_df = (list(gld_df["Date"]))
adj_close_df = list(gld_df["Adj_Close"])
print(adj_close_df)
plt.plot(adj_close_df,date_df)
I would like to plot this Adjusted Close Price on Y-Axis and the corresponding Dates on the X Axis, but my above code is giving an error when I try to do that.
I am using Python 3.x, Anaconda

You could generate the list as below:
l = [ x['Close'] for x in data1]
And the plot:
import matplotlib.pyplot as plt
plt.plot(l)
plt.show()

I got it.
import yahoo_finance
from pylab import *
import numpy as np
import scipy.signal as sc
import matplotlib.pyplot as plt
import pandas as pd
import datetime as dt
ticker = 'GLD'
begdate = '2014-11-11'
enddate = '2016-11-11'
data = yahoo_finance.Share('GLD')
data1 = data.get_historical(begdate,enddate)
gld_df = pd.DataFrame(data1)
date_df = pd.to_datetime((list(gld_df["Date"])))
adj_close_df = list(gld_df["Adj_Close"])
plt.plot(date_df,adj_close_df)

Heatmap with date on horizontal and hour on vertical axis ("fingerprint plot")

I have a pandas data frame with a datetime index and some variable z and I want to reproduce a plot similar to this:
(Image source: University of Edinburgh, http://www.geos.ed.ac.uk/homes/rclement/micromet/Current/griffin/carbon/)
This is often called a "fingerprint plot" in the CO2 flux community.
A year of sample data:
import pandas as pd
import numpy as np
n = 366*24
df = pd.DataFrame(index=pd.date_range(start='2016-01-01 00:00', freq='H', periods=n),
data={'z': np.random.randn(n)})
df["x"] = df.index.date
df["y"] = df.index.hour
df.head()
How do I proceed from here? I played around with the solution to this question:
how to plot a heat map for three column data, but I can't get it to work with the datetime data.

Does this get what you are looking for?
from scipy.interpolate import griddata
from jdcal import jd2jcal
from datetime import datetime
n = 366*24
df = pd.DataFrame(index=pd.date_range(start='2016-01-01 00:00', freq='H', periods=n),
data={'z': np.random.randn(n)})
df["x"] = df.index.date
df["y"] = df.index.hour
df.head()
xi = np.linspace(df.index.to_julian_date().min(), df.index.to_julian_date().max(), 1000)
yi = np.linspace(df.y.min(), df.y.max(), 1000)
zi = griddata((df.index.to_julian_date(),df.index.hour),df.z,(xi[None,:],yi[:,None]),method='linear')
xij = [jd2jcal(0,v) for v in xi]
xid = [datetime(x[0],x[1],x[2]) for x in xij]
plt.contourf(xid,yi,zi)
plt.colorbar()
plt.show()

Plot bar graph using multiple groupby count in panda

I am trying to plot bar graph using pandas. DataTime is index column which I get from timestamp. Here is table structure:
So far i have written this:
import sqlite3
from pylab import *
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import datetime as dt
conn = sqlite3.connect('DEMO2.sqlite')
df = pd.read_sql("SELECT * FROM Data", conn)
df['DateTime'] = df['DATE'].apply(lambda x: dt.date.fromtimestamp(x))
df1 = df.set_index('DateTime', drop=False)
grouped= df1['DateTime'].groupby(lambda x: x.month)
#df1.groupby([df1.index.month, 'DateTime']).count()
grouped.count()
I want output like this:
June has total 4 entry and one entry starts with u. so X has 4 y has 1. Same for July.
Also i want to plot bar graph (X and Y entries) using output. I want MONTH vs Values bar graph

I would created the DataFrame with a dict:
result = pd.DataFrame({'X': g.count(),
'Y': g.apply(lambda x: x.str.startswith('u').sum())})
Now you can use the plot method to plot months vs values.
result.plot()
Note: you can create grouped more efficiently:
grouped = df1['DateTime'].groupby(df1['DateTime'].dt.to_period('M'))
grouped = df1['DateTime'].groupby(df1['DateTime'].dt.month) # if you want Jan-2015 == Jan-2014