I am trying to write a python program that show me the stock price chart for google.
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from pandas_datareader import data as pdr
import yfinance as yf
yf.pdr_override()
#set the start and end date
start_date = "2020-03-01"
end_date = "2020-04-12"
#choose stock ticker symbol
ticker = "GOOGLE"
#get stock price
stock = pdr.get_data_yahoo(ticker, start=start_date, end=end_date)
print(stock)
#obtain dates
stock["Date"]=stock.index.map(mdates.date2num)
#choose figure size
fig = plt.figure(dpi=128, figsize=(10, 6))
#format date to place on the x-axis
formatter = mdates.DateFormatter('%m/%d/%Y')
plt.gca().xaxis.set_major_formatter(formatter)
# Plot data.
plt.plot(stock['Date'], stock['Adj Close'], c='red')
# Format plot.
plt.title("The Stock Price", fontsize=16)
plt.xlabel('Date', fontsize=10)
fig.autofmt_xdate()
plt.ylabel("Price", fontsize=10)
plt.show()
But the program keeps showing me this error.
AttributeError: 'BlockManager' object has no attribute 'refs'
the error keeps focusing on this exception 'Date' somehow during handle it another exception occurred.
Update on the problem: somehow solved itself I don't know how but I run the same code again after 24 h and it gave me the desired output.
Related
I would like to improve my bitcoin dataset but I found that the date is not sorted in the right way and want to show only the month and year. How can I do it?
data = Bitcoin_Historical['Price']
Date1 = Bitcoin_Historical['Date']
train1 = Bitcoin_Historical[['Date','Price']]
#Setting the Date as Index
train2 = train1.set_index('Date')
train2.sort_index(inplace=True)
cols = ['Price']
train2 = train2[cols].apply(lambda x: pd.to_numeric(x.astype(str)
.str.replace(',',''), errors='coerce'))
print (type(train2))
print (train2.head())
plt.figure(figsize=(15, 5))
plt.plot(train2)
plt.xlabel('Date', fontsize=12)
plt.xlim(0,20)
plt.ylabel('Price', fontsize=12)
plt.title("Closing price distribution of bitcoin", fontsize=15)
plt.gcf().autofmt_xdate()
plt.show()
The result shows picture below:
It's not ordered and shows all dates. I would like to order by month+year and show only the month name+year. How can that be done?
Example of Data:
Thank you
I've made the following edits to your code:
converted the column Date column as datetime type
cleaned up the Price column and converting to float
removed the line plt.xlim(0,20) which is causing the output to display 1970
used alternative way to plot, so that the x-axis can be formatted to get monthly tick marks, more info here
Please try the code below:
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
pd.options.mode.chained_assignment = None
Bitcoin_Historical = pd.read_csv('data.csv')
train1 = Bitcoin_Historical[['Date','Price']]
train1['Date'] = pd.to_datetime(train1['Date'], infer_datetime_format=True, errors='coerce')
train1['Price'] = train1['Price'].str.replace(',','').str.replace(' ','').astype(float)
train2 = train1.set_index('Date') #Setting the Date as Index
train2.sort_index(inplace=True)
print (type(train2))
print (train2.head())
ax = train2.plot(figsize=(15, 5))
ax.xaxis.set_major_locator(mdates.MonthLocator(interval=1))
ax.xaxis.set_major_formatter(mdates.DateFormatter('%Y-%b'))
plt.xlabel('Date', fontsize=12)
plt.ylabel('Price', fontsize=12)
plt.title("Closing price distribution of bitcoin", fontsize=15)
plt.show()
Output
Try to cast your "Date" column into datetime, check if it does the trick:
train1.Date = pd.to_datetime(train1.Date)
train2 = train1.set_index('Date')
About matplotlib x-axis date format setting
Hello everyone:
I am learning to write a crawler program in python
Stock information obtained through the yfinance package
Use matplotlib to draw line graphs
But the date format of the axis drawn by matplotlib
Is e.g. 03 Nov 2021, not the matplotlib date format I want
I hope that the date format of the x-axis drawn by matplotlib can be changed
Change to the format of yyyy-mm-dd,
I hope everyone can help
my code:
import yfinance as yf
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib.dates import DateFormatter as mdates
startday = '2021-11-03'
endday = '2021-11-12'
ticker_list = ['2303.TW','2610.TW','2618.TW']
data = pd.DataFrame(columns=ticker_list)
for ticker in ticker_list:
data[ticker] = yf.download(ticker, startday,endday)['Adj Close'] #Get the closing price of the stock market on that day
ans=data.head()
#Start drawing
data.plot(figsize=(8,12))
plt.legend()
plt.rcParams['font.sans-serif'] = ['Microsoft JhengHei']
plt.rcParams['axes.unicode_minus'] = False
plt.title("Line chart change of 7-day closing price of stock market", fontsize=16)
plt.ylabel('closing price', fontsize=14)
plt.xlabel('Day', fontsize=14)
plt.grid(which="major", color='k', linestyle='-.', linewidth=0.5)
plt.show()
print(ans)
You need both a locator and formatter. Reference: https://matplotlib.org/stable/gallery/text_labels_and_annotations/date.html And the way you imported mdates isn't how it's usually done, so I've adjusted that too.
# ... other imports
import matplotlib.dates as mdates
startday = '2021-11-03'
endday = '2021-11-12'
ticker_list = ['2303.TW','2610.TW','2618.TW']
data = pd.DataFrame(columns=ticker_list)
for ticker in ticker_list:
data[ticker] = yf.download(ticker, startday,endday)['Adj Close']
ans=data.head()
data.plot(figsize=(8,12))
plt.legend()
plt.rcParams['font.sans-serif'] = ['Microsoft JhengHei']
plt.rcParams['axes.unicode_minus'] = False
plt.title("Line chart change of 7-day closing price of stock market",
fontsize=16)
plt.ylabel('closing price', fontsize=14)
plt.xlabel('Day', fontsize=14)
plt.grid(which="major", color='k', linestyle='-.', linewidth=0.5)
fmt_day = mdates.DayLocator() # provides a list of days
plt.gca().xaxis.set_major_locator(fmt_day)
plt.gca().xaxis.set_major_formatter(mdates.DateFormatter("%Y-%m-%d"))
plt.show()
I have a graph that shows the closing price of a stock throughout a day at each five minute interval. The x axis shows the time and the range of x values is from 9:30 to 4:00 (16:00).
The problem is that the automatic bounds for the x axis go from 9:37 to 16:07 and I really just want it from 9:30 to 16:00.
The code I am currently running is this:
stk = yf.Ticker(ticker)
his = stk.history(interval="5m", start=start, end=end).values.tolist() #open - high - low - close - volume
x = []
y = []
count = 0
five_minutes = datetime.timedelta(minutes = 5)
for bar in his:
x.append((start + five_minutes * count))#.strftime("%H:%M"))
count = count + 1
y.append(bar[3])
plt.clf()
plt.gca().xaxis.set_major_formatter(mdates.DateFormatter("%H:%M"))
plt.gca().xaxis.set_major_locator(mdates.MinuteLocator(interval=30))
plt.plot(x, y)
plt.gcf().autofmt_xdate()
plt.show()
And it produces this plot (currently a link because I am on a new user account):
I thought I was supposed to use the axis.set_data_interval function providing, so I did so by providing datetime objects representing 9:30 and 16:00 as the min and the max. This gave me the error:
TypeError: '<' not supported between instances of 'float' and 'datetime.datetime'
Is there another a way for me to be able to adjust the first xtick and still have it automatically fill in the rest?
This problem can be fixed by adjusting the way you use the mdates tick locator. Here is an example based on the one shared by r-beginners to make it comparable. Note that I use the pandas plotting function for convenience. The x_compat=True argument is needed for it to work with mdates:
import pandas as pd # 1.1.3
import yfinance as yf # 0.1.54
import matplotlib.dates as mdates # 3.3.2
# Import data
ticker = 'AAPL'
stk = yf.Ticker(ticker)
his = stk.history(period='1D', interval='5m')
# Create pandas plot with appropriately formatted x-axis ticks
ax = his.plot(y='Close', x_compat=True, figsize=(10,5))
ax.xaxis.set_major_locator(mdates.MinuteLocator(byminute=[0, 30]))
ax.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M', tz=his.index.tz))
ax.legend(frameon=False)
ax.figure.autofmt_xdate(rotation=0, ha='center')
The sample data was created by obtaining Apple's stock price from Yahoo Finance. The desired five-minute interval labels are a list of strings obtained by using the date function to get the start and end times at five-minute intervals.
Based on this, the x-axis is drawn as a graph of the number of five-minute intervals and the closing price, and the x-axis is set to any interval by slicing.
import yfinance as yf
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import pandas as pd
import numpy as np
ticker = 'AAPL'
stk = yf.Ticker(ticker)
his = stk.history(period='1D',interval="5m")
his.reset_index(inplace=True)
time_rng = pd.date_range('09:30','15:55', freq='5min')
labels = ['{:02}:{:02}'.format(t.hour,t.minute) for t in time_rng]
fig, ax = plt.subplots()
x = np.arange(len(his))
y = his.Close
ax.plot(x,y)
ax.set_xticks(x[::3])
ax.set_xticklabels(labels[::3], rotation=45)
plt.show()
I am new to Python and learning data visualization using matplotlib.
I am trying to plot Date/Time vs Values using matplotlib from this CSV file:
https://drive.google.com/file/d/1ex2sElpsXhxfKXA4ZbFk30aBrmb6-Y3I/view?usp=sharing
Following is the code snippet which I have been playing around with:
import pandas as pd
from matplotlib import pyplot as plt
import matplotlib.dates as mdates
plt.style.use('seaborn')
years = mdates.YearLocator()
months = mdates.MonthLocator()
days = mdates.DayLocator()
hours = mdates.HourLocator()
minutes = mdates.MinuteLocator()
years_fmt = mdates.DateFormatter('%H:%M')
data = pd.read_csv('datafile.csv')
data.sort_values('Date/Time', inplace=True)
fig, ax = plt.subplots()
ax.plot('Date/Time', 'Discharge', data=data)
# format the ticks
ax.xaxis.set_major_locator(minutes)
ax.xaxis.set_major_formatter(years_fmt)
ax.xaxis.set_minor_locator(hours)
datemin = min(data['Date/Time'])
datemax = max(data['Date/Time'])
ax.set_xlim(datemin, datemax)
ax.format_xdata = mdates.DateFormatter('%Y.%m.%d %H:%M')
ax.format_ydata = lambda x: '%1.2f' % x # format the price.
ax.grid(True)
fig.autofmt_xdate()
plt.show()
The code is plotting the graph but it is not labeling the X-Axis and also giving some unknown values (on mouse over) for x on the bottom right corner as shown in the below screenshot:
Screenshot of matplotlib figure window
Can someone please suggest what changes are needed to plot the x-axis dates and also make the correct values appear when I move the cursor over the graph?
Thanks
I haven't used matplotlib. Instead I used pandas plotting
import pandas as pd
data = pd.read_csv('datafile.csv')
data.sort_values('Date/Time', inplace=True)
data["Date/Time"] = pd.to_datetime(data["Date/Time"], format="%d.%m.%Y %H:%M")
ax = data.plot.line(x='Date/Time', y='Discharge')
Here, you need to convert the Date/Time to pandas datetime type.
The main issue you have there is that the date formats are mixed up - your data uses '%d.%m.%Y %H:%M', but you set '%Y.%m.%d %H:%M' and this is why you saw 'rubbish' values in x ticks labels. Anyway the number of lines in your code can be reduced heavily if you convert your Date/Time column to timestamps, ie.:
import pandas as pd
from matplotlib import pyplot as plt
import matplotlib.dates as mdates
plt.style.use('seaborn')
data = pd.read_csv('datafile.csv')
data.sort_values('Date/Time', inplace=True)
data["Date/Time"] = pd.to_datetime(data["Date/Time"], format="%d.%m.%Y %H:%M")
data.sort_values('Date/Time', inplace=True)
fig, ax = plt.subplots()
ax.plot('Date/Time', 'Discharge', data=data)
ax.format_xdata = mdates.DateFormatter('%Y.%m.%d %H:%M')
ax.tick_params(axis='x', rotation=45)
ax.grid(True)
fig.autofmt_xdate()
plt.show()
Note that the format of labels in the plot will depend on the zoom level, so you will need to enlarge a portion of the graph to see hours and minutes in the tick labels, but the cursor locator on the bottom bar of the window should be always displaying the detailed timestamp under the cursor.
I am trying to manually create a candlestick chart with matplotlib using errorbar for the daily High and Low prices and Rectangle() for the Adjusted Close and Open prices. This question seemed to have all the prerequisites for accomplishing this.
I attempted to use the above very faithfully, but the issue of plotting something over an x-axis of datetime64[ns]'s gave me no end of errors, so I've additionally tried to incorporate the advice here on plotting over datetime.
This is my code so far, with apologies for the messiness:
import pandas as pd
import datetime as dt
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from matplotlib.collections import PatchCollection
from matplotlib.patches import Rectangle
def makeCandles(xdata,high,low,adj_close,adj_open,fc='r',ec='None',alpha=0.5):
## Converting datetimes to numerical format matplotlib can understand.
dates = mdates.date2num(xdata)
## Creating default objects
fig,ax = plt.subplots(1)
## Creating errorbar peaks based on high and low prices
avg = (high + low) / 2
err = [high - avg,low - avg]
ax.errorbar(dates,err,fmt='None',ecolor='k')
## Create list for all the error patches
errorboxes = []
## Loop over data points; create "body" of candlestick
## based on adjusted open and close prices
errors=np.vstack((adj_close,adj_open))
errors=errors.T
for xc,yc,ye in zip(dates,avg,errors):
rect = Rectangle((xc,yc-ye[0]),1,ye.sum())
errorboxes.append(rect)
## Create patch collection with specified colour/alpha
pc = PatchCollection(errorboxes,facecolor=fc,alpha=alpha,edgecolor=ec)
## Add collection to axes
ax.add_collection(pc)
plt.show()
With my data looking like
This is what I try to run, first getting a price table from quandl,
import quandl as qd
api = '1uRGReHyAEgwYbzkPyG3'
qd.ApiConfig.api_key = api
data = qd.get_table('WIKI/PRICES', qopts = { 'columns': ['ticker', 'date', 'high','low','adj_open','adj_close'] }, \
ticker = ['AMZN', 'XOM'], date = { 'gte': '2014-01-01', 'lte': '2016-12-31' })
data.reset_index(inplace=True,drop=True)
makeCandles(data['date'],data['high'],data['low'],data['adj_open'],data['adj_close'])
The code runs with no errors, but outputs an empty graph. So what I am asking for is advice on how to plot these rectangles over the datetime dates. For the width of the rectangles, I simply put a uniform "1" bec. I am not aware of a simple way to specify the datetime width of a rectangle.
Edit
This is the plot I am currently getting, having transformed my xdata into matplotlib mdates:
Before I transformed xdata via mdates, with just xdata as my x-axis everywhere, this was one of the errors I kept getting:
To get the plot you want, there's a couple of things that need to be considered. First you're retrieving to stocks AMZN and XOM, displaying both will make the chart you want look funny, because the data are quite far apart. Second, candlestick charts in which you plot each day for several years will get very crowded. Finally, you need to format your ordinal dates back on the x-axis.
As mentioned in the comments, you can use the pre-built matplotlib candlestick2_ohlc function (although deprecated) accessible through mpl_finance, install as shown in this answer. I opted for using solely the matplotlib barchart with built-in errorbars.
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import quandl as qd
from matplotlib.dates import DateFormatter, WeekdayLocator, \
DayLocator, MONDAY
# get data
api = '1uRGReHyAEgwYbzkPyG3'
qd.ApiConfig.api_key = api
data = qd.get_table('WIKI/PRICES', qopts={'columns': ['ticker', 'date', 'high', 'low', 'open', 'close']},
ticker=['AMZN', 'XOM'], date={'gte': '2014-01-01', 'lte': '2014-03-10'})
data.reset_index(inplace=True, drop=True)
fig, ax = plt.subplots(figsize = (10, 5))
data['date'] = mdates.date2num(data['date'].dt.to_pydatetime()) #convert dates to ordinal
tickers = list(set(data['ticker'])) # unique list of stock names
for stock_ind in tickers:
df = data[data['ticker'] == 'AMZN'] # select one, can do more in a for loop, but it will look funny
inc = df.close > df.open
dec = df.open > df.close
ax.bar(df['date'][inc],
df['open'][inc]-df['close'][inc],
color='palegreen',
bottom=df['close'][inc],
# this yerr is confusing when independent error bars are drawn => (https://matplotlib.org/api/pyplot_api.html#matplotlib.pyplot.errorbar)
yerr = [df['open'][inc]-df['high'][inc], -df['open'][inc]+df['low'][inc]],
error_kw=dict(ecolor='gray', lw=1))
ax.bar(df['date'][dec],
df['close'][dec]-df['open'][dec],
color='salmon', bottom=df['open'][dec],
yerr = [df['close'][dec]-df['high'][dec], -df['close'][dec]+df['low'][dec]],
error_kw=dict(ecolor='gray', lw=1))
ax.set_title(stock_ind)
#some tweaking, setting the dates
mondays = WeekdayLocator(MONDAY) # major ticks on the mondays
alldays = DayLocator() # minor ticks on the days
weekFormatter = DateFormatter('%b %d') # e.g., Jan 12
dayFormatter = DateFormatter('%d') # e.g., 12
ax.xaxis.set_major_locator(mondays)
ax.xaxis.set_minor_locator(alldays)
ax.xaxis.set_major_formatter(weekFormatter)
ax.set_ylabel('monies ($)')
plt.show()