I have written the code below to visualise a joyplot. When trying to change the x axis labels using axes.set_xticks, I get the error: AttributeError: 'list' object has no attribute 'set_xticks'
import joypy
import pandas as pd
from matplotlib import pyplot as plt
data = pd.DataFrame.from_records([['twitter', 1],
['twitter', 6],
['wikipedia', 1],
['wikipedia', 3],
['indymedia', 1],
['indymedia', 9]], columns=['platform','day'])
# Get number of days in the dataset
numdays = max(set(data['day'].tolist()))
# Generate date strings from a manually set start date
start_date = "2010-01-01"
dates = pd.date_range(start_date, periods=numdays)
dates = [str(date)[:-9] for date in dates]
fig, axes = joypy.joyplot(data,by="platform")
axes.set_xticks(range(numdays)); axes.set_xticklabels(dates)
plt.show()
The expected output should look something like the following but with the dates from dates as ticklabels.
Since joypy.joyplot(..) returns a tuple of figure, axes and axes should be list of axes, you probably want to set the labels for the last axes,
axes[-1].set_xticks(range(numdays))
axes[-1].set_xticklabels(dates)
To make date plots with python matplotlib do you should use plot_date function.
fig, ax = plt.subplots()
ax.plot_date(dates, data1, '-')
I put the complete example in pastebin, follow the link:
https://pastebin.com/sVPUZaeM
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.dates import DateFormatter
from random import randrange, random
from datetime import datetime
#generate date list
start_date = np.datetime64('2010-01-01').astype(datetime)
numdays = 10
dates = pd.date_range(start_date, periods=numdays)
#Generate data example
data1 = [(random()+idx)**1.2 for idx in range(len(dates))]
data2 = [(random()+idx)**1.5 for idx in range(len(dates))]
#plot
fig, ax = plt.subplots()
ax.plot_date(dates, data1, '-')
ax.plot_date(dates, data2, '-')
#set the label for x and y and title
plt.title('Matplot lib dates wc example')
plt.xlabel('Dates')
plt.ylabel('Random values example')
#date format
ax.fmt_xdata = DateFormatter('%Y%m%d')
ax.grid(True)
fig.autofmt_xdate()
plt.show()
Python version tested successfully: 2.7.12
This code generates: this follow plot
Related
I have a simple dataframe with the time as index and dummy values as example.[]
I did a simple scatter plot as you see here:
Simple question: How to adjust the xaxis, so that all time values from 00:00 to 23:00 are visible in the xaxis? The rest of the plot is fine, it shows all the datapoints, it is just the labeling. Tried different things but didn't work out.
All my code so far is:
import pandas as pd
import seaborn as sns
import matplotlib.dates as mdates
from datetime import time
data = []
for i in range(0, 24):
temp_list = []
temp_list.append(time(i))
temp_list.append(i)
data.append(temp_list)
my_df = pd.DataFrame(data, columns=["time", "values"])
my_df.set_index(['time'],inplace=True)
my_df
fig = sns.scatterplot(my_df.index, my_df['values'])
fig.set(xlabel='time', ylabel='values')
I think you're gonna have to go down to the matplotlib level for this:
import pandas as pd
import seaborn as sns
import matplotlib.dates as mdates
from datetime import time
import matplotlib.pyplot as plt
data = []
for i in range(0, 24):
temp_list = []
temp_list.append(time(i))
temp_list.append(i)
data.append(temp_list)
df = pd.DataFrame(data, columns=["time", "values"])
df.time = pd.to_datetime(df.time, format='%H:%M:%S')
df.set_index(['time'],inplace=True)
ax = sns.scatterplot(df.index, df["values"])
ax.set(xlabel="time", ylabel="measured values")
ax.set_xlim(df.index[0], df.index[-1])
ax.xaxis.set_major_locator(mdates.HourLocator())
ax.xaxis.set_major_formatter(mdates.DateFormatter("%H:%M:%S"))
ax.tick_params(axis="x", rotation=45)
This produces
i think you have 2 options:
convert the time to hour only, for that just extract the hour to new column in your df
df['hour_'] = datetime.hour
than use it as your xaxis
if you need the time in the format you described, it may cause you a visibility problem in which timestamps will overlay each other. i'm using the
plt.xticks(rotation=45, horizontalalignment='right')
ax.xaxis.set_major_locator(plt.MaxNLocator(12))
so first i rotate the text then i'm limiting the ticks number.
here is a full script where i used it:
sns.set()
sns.set_style("whitegrid")
sns.axes_style("whitegrid")
for k, g in df_forPlots.groupby('your_column'):
fig = plt.figure(figsize=(10,5))
wide_df = g[['x', 'y', 'z']]
wide_df.set_index(['x'], inplace=True)
ax = sns.lineplot(data=wide_df)
plt.xticks(rotation=45,
horizontalalignment='right')
ax.yaxis.set_major_locator(plt.MaxNLocator(14))
ax.xaxis.set_major_locator(plt.MaxNLocator(35))
plt.title(f"your {k} in somthing{g.z.unique()}")
plt.tight_layout()
hope i halped
I am trying to use the following code to set the x-ticks to [Jan., Feb., ...]
import matplotlib.pyplot as plt
from matplotlib.dates import MonthLocator, DateFormatter
fig = plt.figure(figsize=[10, 5])
ax = fig.add_subplot(111)
ax.plot(np.arange(1000))
ax.xaxis.set_major_locator(MonthLocator())
ax.xaxis.set_major_formatter(DateFormatter('%b'))
I get the following figure, without x-ticks
I'm wondering why all x-ticks disappeared? I wrote the above code with reference to this implementation
Many thanks.
It is not very clear the type of data you currently have. But below are my suggestions for plotting the month on the x-axis:
Transform your date using pd.to_datetime
Set it to your dataframe index.
Call explicitly the plt.set_xticks() method
Below one example with re-created data:
from datetime import datetime as dt
from datetime import timedelta
### create sample data
your_df = pd.DataFrame()
your_df['vals'] = np.arange(1000)
## make sure your datetime is considered as such by pandas
your_df['date'] = pd.to_datetime([dt.today()+timedelta(days=x) for x in range(1000)])
your_df= your_df.set_index('date') ## set it as index
### plot it
fig = plt.figure(figsize=[10, 5])
ax = fig.add_subplot(111)
ax.plot(your_df['vals'])
plt.xticks(rotation='vertical')
ax.xaxis.set_major_locator(MonthLocator())
ax.xaxis.set_major_formatter(DateFormatter('%b'))
Note that if you do not want every month plotted, you can let matplotlib handle that for you, by removing the major locator.
fig = plt.figure(figsize=[10, 5])
ax = fig.add_subplot(111)
ax.plot(your_df['vals'])
plt.xticks(rotation='vertical')
# ax.xaxis.set_major_locator(MonthLocator())
ax.xaxis.set_major_formatter(DateFormatter('%b'))
Added Went into the link provided, and you do have a DATE field in the dataset used (boulder-precip.csv). You can actually follow the same procedure and have it plotted on a monthly-basis:
df = pd.read_csv('boulder-precip.csv')
df['DATE'] = pd.to_datetime(df['DATE'])
df = df.set_index('DATE')
fig = plt.figure(figsize=[10, 5])
ax = fig.add_subplot(111)
ax.plot(df['PRECIP'])
plt.xticks(rotation='vertical')
ax.xaxis.set_major_locator(MonthLocator())
ax.xaxis.set_major_formatter(DateFormatter('%b'))
I have a dataframe that I want the x axis to show as APR-2018 for example. The ax.format_xdata line does not do the trick.
import datetime as dt
import pandas as pd
import time
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
data = {("IVOG",1493510400000):{"Adj_Close":119.2136,"MA(3)":119.2136,"EWMA(3)":119.2136},
("IVOG",1496188800000):{"Adj_Close":120.8236,"MA(3)":120.0186,"EWMA(3)":120.0454},
("IVOG",1498780800000):{"Adj_Close":120.2736,"MA(3)":120.1036,"EWMA(3)":120.1266},
("IVOG",1501459200000):{"Adj_Close":121.7836,"MA(3)":120.5236,"EWMA(3)":120.5832},
("IVOG",1504137600000):{"Adj_Close":120.3536,"MA(3)":120.4896,"EWMA(3)":120.5309},
("IVOG",1506729600000):{"Adj_Close":124.3336,"MA(3)":121.1303,"EWMA(3)":121.2749}}
df=pd.DataFrame.from_dict(data, orient = 'index')
print(df)
ax = plt.gca() # get current axis
df.plot(kind='line',y='Adj_Close', ax=ax)
df.plot(kind='line',y='MA(3)',ax=ax)
df.plot(kind='line',y='EWMA(3)', color='green', ax=ax)
print(df.index[0][1])
ax.format_xdata = mdates.DateFormatter('%b-%Y') # Trying to get APR-2018
plt.xlabel(df.index[0][0]) # Trying to Get the Ticker
_=plt.grid()
_=plt.xticks(rotation=90)
plt.show()
The second index should be just the date and not time, but it incorrectly plots like this:Incorrect Plot
This should do the trick. Of course there are 'prettier' ways, but I have tried to make it so that you can keep your data and original data frame as close as to the original one in your question.
Edited after comments: so how about this, just create a new column with the date that you format in whatever shape you want. Then use set_xticklabels() passing that column to set the ticks as you want. Also you might want to remove the default plt.xlabel (otherwise you would have below your xticks the name of the indexes).
import datetime as dt
import pandas as pd
import time
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
# the first part of your code is the same
data = {("IVOG",1493510400000):{"Adj_Close":119.2136,"MA(3)":119.2136,"EWMA(3)":119.2136},
("IVOG",1496188800000):{"Adj_Close":120.8236,"MA(3)":120.0186,"EWMA(3)":120.0454},
("IVOG",1498780800000):{"Adj_Close":120.2736,"MA(3)":120.1036,"EWMA(3)":120.1266},
("IVOG",1501459200000):{"Adj_Close":121.7836,"MA(3)":120.5236,"EWMA(3)":120.5832},
("IVOG",1504137600000):{"Adj_Close":120.3536,"MA(3)":120.4896,"EWMA(3)":120.5309},
("IVOG",1506729600000):{"Adj_Close":124.3336,"MA(3)":121.1303,"EWMA(3)":121.2749}}
df=pd.DataFrame.from_dict(data, orient = 'index')
# first let's give a name to the indexes
df.index.names = ['ivog', 'timestamp']
# then create a new column with a datetime object
# (formatted to microseconds as your data seems to be)
df['date'] = pd.to_datetime(df.index.levels[1],
unit='ms')
# now let's change the date to the format you want
df['date'] = df['date'].apply(lambda x: x.strftime("%Y %B"))
print(df)
# plot the data just like you were doing
ax = plt.gca() # get current axis
df.plot(kind='line',y='Adj_Close', ax=ax)
df.plot(kind='line',y='MA(3)',ax=ax)
df.plot(kind='line',y='EWMA(3)', color='green', ax=ax)
# Now the x-axis label should be what you wished for
ax.set_xticklabels(df['date'])
plt.xlabel('Your x axis label')
plt.ylabel('Your y axis label')
plt.title('My Awseome Plot')
plt.xticks(rotation=45)
trying to plot a candlestick serie after importing datas from yahoo-finance. I'm using python 2.7
I have already a serie plotted and I want to add the same one as candlestick but I don't see how I can do that :
import matplotlib.pyplot as plt
from matplotlib.finance import candlestick2_ohlc
#Reset the index to remove Date column from index
df_ohlc = data.reset_index()
#Naming columns
df_ohlc.columns = ["Date","Open","High",'Low',"Close", "Adj Close", "Volume"]
#Normal plot
ax1 = plt.subplot()
ax1.plot(df_ohlc["Date"], df_ohlc["Close"], label = "Price", color="blue", linewidth=2.0)
#Candle plot
candlestick2_ohlc(ax1,df_ohlc['Open'],df_ohlc['High'],df_ohlc['Low'],df_ohlc['Close'],width=0.6)
If I plot candlestick alone, it looks fine but the x axis is a list of integers.
If I plot candlestick alone after converting df_ohlc["Date"] to float then reconverting to datetime, it plots the serie with the correct x axis but there are gaps on the weekend even if the serie isn't defined for these dates.
Is there a way to plot both series at the same time ? I'm planning to add more series like moving average, OLS, Bollinger etc...
You can remove weekend gaps and make human-readable dates xticklabels in this way. Note that, this script is written in python 3 and there may be some differences from python 2.
import quandl
import numpy as np
from mpl_finance import candlestick_ohlc
import matplotlib.pyplot as plt
# getting data and modifying it to remove gaps at weekends
r = quandl.get('WIKI/AAPL', start_date='2016-01-01', end_date='2017-11-10')
date_list = np.array(r.index.to_pydatetime())
plot_array = np.zeros([len(r), 5])
plot_array[:, 0] = np.arange(plot_array.shape[0])
plot_array[:, 1:] = r.iloc[:, :4]
# plotting candlestick chart
fig, ax = plt.subplots()
num_of_bars = 100 # the number of candlesticks to be plotted
candlestick_ohlc(ax, plot_array[-num_of_bars:], colorup='g', colordown='r')
ax.margins(x=0.0, y=0.1)
ax.yaxis.tick_right()
x_tick_labels = []
ax.set_xlim(right=plot_array[-1, 0]+10)
ax.grid(True, color='k', ls='--', alpha=0.2)
# setting xticklabels actual dates instead of numbers
indices = np.linspace(plot_array[-num_of_bars, 0], plot_array[-1, 0], 8, dtype=int)
for i in indices:
date_dt = date_list[i]
date_str = date_dt.strftime('%b-%d')
x_tick_labels.append(date_str)
ax.set(xticks=indices, xticklabels=x_tick_labels)
plt.show()
I really need more information about your code and your dataframe, but you can use this example to do a candlestick
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.ticker as mticker
from matplotlib.finance import candlestick_ohlc
import matplotlib.dates as mdates
import datetime as dt
#Reset the index to remove Date column from index
df_ohlc = df.reset_index()
#Naming columns
df_ohlc.columns = ["Date","Open","High",'Low',"Close", "Adj Close", "Volume"]
#Converting dates column to float values
df_ohlc['Date'] = df_ohlc['Date'].map(mdates.date2num)
#Making plot
fig = plt.figure()
fig.autofmt_xdate()
ax1 = plt.subplot2grid((6,1), (0,0), rowspan=6, colspan=1)
#Converts raw mdate numbers to dates
ax1.xaxis_date()
plt.xlabel("Date")
print(df_ohlc)
#Making candlestick plot
candlestick_ohlc(ax1,df_ohlc.values,width=1, colorup='g', colordown='k',alpha=0.75)
plt.ylabel("Price")
plt.legend()
plt.show()
I am plotting two pandas series. The index is a date (1-1 to 12-31)
s1.plot()
s2.plot()
pd.plot() interprets the dates and assigns them to axis values as such:
I would like to modify the major ticks to be the 1st of every month and minor ticks to be the days in between
This works:
%matplotlib notebook
import matplotlib as mpl
import matplotlib.dates as mdates
import matplotlib.pyplot as plt
import pandas as pd
df = pd.read_csv('data.csv')
df['Date'] = pd.to_datetime(df['Date']).dt.strftime('%m-%d')
s2014max = df2014.groupby(['Date'], sort=True)['Data_Value'].max()/10
s2014min = df2014.groupby(['Date'], sort=True)['Data_Value'].min()/10
#remove the leap day and convert to datetime for plotting
s2014min = s2014min[s2014min.index != '02-29']
s2014max = s2014max[s2014max.index != '02-29']
dateslist = s2014min.index.tolist()
dates = [pd.datetime.strptime(date, '%m-%d').date() for date in dateslist]
plt.figure()
ax = plt.gca()
ax.xaxis.set_major_locator(mdates.MonthLocator())
ax.xaxis.set_minor_locator(mdates.DayLocator())
monthFmt = mdates.DateFormatter('%b')
dayFmt = mdates.DateFormatter('%d')
ax.xaxis.set_major_formatter(monthFmt)
ax.xaxis.set_minor_formatter(dayFmt)
ax.tick_params(direction='out', pad=15)
s2014min.plot()
s2014max.plot()
This results in no ticks:
A possible way is to use matplotlib for plotting the dates instead of pandas.
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import numpy as np
dates = pd.date_range("2016-01-01", "2016-12-31" )
y = np.cumsum(np.random.normal(size=len(dates)))
df = pd.DataFrame({"Dates" : dates, "y": y})
fig, ax = plt.subplots()
ax.plot_date(df["Dates"], df.y, '-')
ax.xaxis.set_major_locator(mdates.MonthLocator())
ax.xaxis.set_minor_locator(mdates.DayLocator())
monthFmt = mdates.DateFormatter('%b')
ax.xaxis.set_major_formatter(monthFmt)
plt.show()
You were so close! All you needed to do was add the formatters similar to how the other answer did it. Here is a working sample similar to your code (note I did mine in ipython notebook hence the %matplotlib inline).
%matplotlib inline
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from datetime import datetime, timedelta
from random import random
y = [random() for i in range(25)]
x = [(datetime.now() - timedelta(days=i)) for i in range(25)]
x.reverse()
s = pd.Series(y, index=x) # NOTE: S, not df, since you said you were using series
# format the ticks
ax = plt.gca()
ax.xaxis.set_major_locator(mdates.MonthLocator())
ax.xaxis.set_minor_locator(mdates.DayLocator())
monthFmt = mdates.DateFormatter('%b')
dayFmt = mdates.DateFormatter('%d')
ax.xaxis.set_major_formatter(monthFmt) # This is what you needed
ax.xaxis.set_minor_formatter(dayFmt) # This is what you needed
ax.tick_params(direction='out', pad=15)
# format the coords message box
s.plot(figsize=(10,3))
which will look like this: