I want to plot data for custom date range . So my data set is like every day from 8 a.m. to 5 p.m. I need to plot this time ranges for 5 days. How can i do that so that i dont get the other time range apart from the above mentioned. I tried plotting using x locator but it shows the data in full time range.
tried setting x locator didn't work
import datetime
from matplotlib import dates as mdates
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.dates
x= pd.date_range(start=datetime.datetime( 2019, 7, 8, 8, 0,0 ), freq='10min',end=datetime.datetime ( 2019, 7, 12, 17, 0 ,0))
start = datetime.time(8, 0, 0)
end = datetime.time(17, 0, 0)
def time_in_range(start, end, x):
"""Return true if x is in the range [start, end]"""
if start <= end:
return start <= x <= end
else:
return start <= x or x <= end
t= [i.to_datetime() for i in x if time_in_range(start,end,i.to_datetime().time())]
df=pd.DataFrame({'d':d,'t':t})
df=df.set_index('t')
fig,axes = plt.subplots()
axes.xaxis_date()
axes.bar(mdates.date2num(list(df.index)),df['d'],align='center',width=0.006,color='pink')
fig.autofmt_xdate()
xformatter = mdates.DateFormatter('%d/%m/%y:%H:%M')
xlocator = mdates.HourLocator(byhour=range(8,17,2))
axes.xaxis.set_major_locator(xlocator)
plt.gcf().axes[0].xaxis.set_major_formatter(xformatter)
plt.show()
Related
I have a dataframe (df) as following
id date t_slot dayofweek label
1 2021-01-01 2 0 1
1 2021-01-02 3 1 0
2 2021-01-01 4 6 1
.......
The data frame is very large(6 million rows). the t_slot is from 1 to 6 value. dayofweek is from 0-6.
I want to get the rate:
- the each id's rate about the label is 1 rate when the t_slot is 1 to 4, and dayofweek is 0-4 in the past 3 months before the date in each row.
- the each id's rate about the label is 1 rate when the t_slot is 1 to 4, and dayofweek is 0-4 in the past 3 months before the date in each row.
- the each id's rate about the label is 1 rate when the t_slot is 5 to 6, and dayofweek is 5-6 in the past 3 months before the date in each row.
- the each id's rate about the label is 1 rate when the t_slot is 5 to 6, and dayofweek is 5-6 in the past 3 months before the date in each row.
I have used loop to compute the rate, but it is very slow, do you have fast way to compute it. My code is copied as following:
def get_time_slot_rate(df):
import numpy as np
if len(df)==0:
return np.nan, np.nan, np.nan, np.nan
else:
work = df.loc[df['dayofweek']<5]
weekend = df.loc[df['dayofweek']>=5]
if len(work)==0:
work_14, work_56 = np.nan, np.nan
else:
work_14 = len(work.loc[(work['time_slot']<5)*(work['label']==1)])/len(work)
work_56 = len(work.loc[(work['time_slot']>5)*(work['label']==1)])/len(work)
if len(weekend)==0:
weekend_14, weekend_56 = np.nan, np.nan
else:
weekend_14 = len(weekend.loc[(weekend['time_slot']<5)*(weekend['label']==1)])/len(weekend)
weekend_56 = len(weekend.loc[(weekend['time_slot']>5)*(weekend['label']==1)])/len(weekend)
return work_14, work_56, weekend_14, weekend_56
import datetime as d_t
lst_id = list(df['id'])
lst_date = list(df['date'])
lst_t14_work = []
lst_t56_work = []
lst_t14_weekend = []
lst_t56_weekend = []
for i in range(len(lst_id)):
if i%100==0:
print(i)
d_date = lst_date[i]
dt = d_t.datetime.strptime(d_date, '%Y-%m-%d')
month_step = relativedelta(months=3)
pre_date = str(dt - month_step).split(' ')[0]
df_s = df.loc[(df['easy_id']==lst_easy[i])
& ((df['delivery_date']>=pre_date)
&(df['delivery_date']< d_date))].reset_index(drop=True)
work_14_rate, work_56_rate, weekend_14_rate, weekend_56_rate = get_time_slot_rate(df_s)
lst_t14_work.append(work_14_rate)
lst_t56_work.append(work_56_rate)
lst_t14_weekend.append(weekend_14_rate)
lst_t56_weekend.append(weekend_56_rate)
I could only fix your function and it's completely untested, but here we go:
Import only once by putting the imports at the top of your .py.
try/except blocks are more efficient than if/else statements.
True and False equals to 1 and 0 respectively in Python.
Don't multiply boolean selectors and use the reverse operator ~
Create the least amount of copies.
import numpy as np
def get_time_slot_rate(df):
# much faster than counting
if df.empty:
return np.nan, np.nan, np.nan, np.nan
# assuming df['label'] is either 0 or 1
df = df.loc[df['label']]
# create boolean selectors to be inverted with '~'
weekdays = df['dayofweek']<=5
slot_selector = df['time_slot']<=5
weekday_count = np.sum(weekdays)
try:
work_14 = len(df.loc[weekdays & slot_selector])/weekday_count
work_56 = len(df.loc[weekdays & ~slot_selector])/weekday_count
except ZeroDivisionError:
work_14 = work_56 = np.nan
weekend_count = np.sum(~weekdays)
try:
weekend_14 = len(df.loc[~weekdays & slot_selector])/weekend_count
weekend_56 = len(df.loc[~weekdays & ~slot_selector])/weekend_count
except ZeroDivisionError:
weekend_14 = weekend_56 = np.nan
return work_14, work_56, weekend_14, weekend_56
The rest of your script doesn't really make sense, see my comments:
for i in range(len(lst_id)):
if i%100==0:
print(i)
d_date = date[i]
# what is d_t ?
dt = d_t.datetime.strptime(d_date, '%Y-%m-%d')
month_step = relativedelta(months=3)
pre_date = str(dt - month_step).split(' ')[0]
df_s = df.loc[(df['easy_id']==lst_easy[i])
& (df['delivery_date']>=pre_date)
&(df['delivery_date']< d_date)].reset_index(drop=True)
# is it df or df_s ?
work_14_rate, work_56_rate, weekend_14_rate, weekend_56_rate = get_time_slot_rate(df)
If your date column is a datetime object than you can compare dates directly (no need for strings).
I would be grateful if you can help me solve the problem
import matplotlib.pyplot as plt
import tifffile as tiff
import os
rows = 3
cols = 4
axes=[]
fig=plt.figure(figsize=[10,10])
i=["/images/1","/masks/1","/images/2","/masks/2"]
i=i+["/images/3","/masks/3","/images/4","/masks/4"]
p=1
m=0
for a in range(rows*cols):
if i[m].find("masks")!=-1:
b = plt.imread("/content/drive/MyDrive/PFE_MOHTICH/dataset/data/test{}.png".format(str(i[m])))
else:
b = tiff.imread("/content/drive/MyDrive/PFE_MOHTICH/dataset/data/test{}.tiff".format(str(i[m])))
m=m+1
axes.append( fig.add_subplot(rows, cols, a+1) )
plt.imshow(b)
plt.savefig("ex_val.png",cmap='binary_r')
fig.tight_layout()
plt.show()
The line which results in an error
(if i[m].find("masks")!=-1) :
the error message:
list index out of range
I don't know what's hard to see in this. Your for loop
for a in range(rows*cols): #rows*cols = (3*4) = 12
# In this loop you update m every iteration
m = m+1
so your m goes from 0 to 11 while your i has only 8 elements.
Like what is it that you can't see/get?
Plot 4 different line plots for the 4 companies in dataframe open_prices. Year would be on X-axis, stock price on Y axis, you will need (2,2) plot. Set figure size to 10, 8 and share X-axis for better visualization
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from nsepy import get_history
import datetime as dt
%matplotlib inline
start = dt.datetime(2015, 1, 1)
end = dt.datetime.today()
infy = get_history(symbol='INFY', start = start, end = end)
infy.index = pd.to_datetime(infy.index)
hdfc = get_history(symbol='HDFC', start = start, end = end)
hdfc.index = pd.to_datetime(hdfc.index)
reliance = get_history(symbol='RELIANCE', start = start, end = end)
reliance.index = pd.to_datetime(reliance.index)
wipro = get_history(symbol='WIPRO', start = start, end = end)
wipro.index = pd.to_datetime(wipro.index)
open_prices = pd.concat([infy['Open'], hdfc['Open'],reliance['Open'],
wipro['Open']], axis = 1)
open_prices.columns = ['Infy', 'Hdfc', 'Reliance', 'Wipro']
f, (ax1, ax2) = plt.subplots(1, 2, sharey=True)
axes[0, 0].plot(open_prices.index.year,open_prices.INFY)
axes[0, 1].plot(open_prices.index.year,open_prices.HDB)
axes[1, 0].plot(open_prices.index.year,open_prices.TTM)
axes[1, 1].plot(open_prices.index.year,open_prices.WIT)
Blank graph is coming.Please help....?!??
Below code works fine , I have changed the following things
a) axis should be ax b) DF column names were incorrect c) for any one to try this example would also need to install lxml library
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from nsepy import get_history
import datetime as dt
start = dt.datetime(2015, 1, 1)
end = dt.datetime.today()
infy = get_history(symbol='INFY', start = start, end = end)
infy.index = pd.to_datetime(infy.index)
hdfc = get_history(symbol='HDFC', start = start, end = end)
hdfc.index = pd.to_datetime(hdfc.index)
reliance = get_history(symbol='RELIANCE', start = start, end = end)
reliance.index = pd.to_datetime(reliance.index)
wipro = get_history(symbol='WIPRO', start = start, end = end)
wipro.index = pd.to_datetime(wipro.index)
open_prices = pd.concat([infy['Open'], hdfc['Open'],reliance['Open'],
wipro['Open']], axis = 1)
open_prices.columns = ['Infy', 'Hdfc', 'Reliance', 'Wipro']
print(open_prices.columns)
ax=[]
f, ax = plt.subplots(2, 2, sharey=True)
ax[0,0].plot(open_prices.index.year,open_prices.Infy)
ax[1,0].plot(open_prices.index.year,open_prices.Hdfc)
ax[0,1].plot(open_prices.index.year,open_prices.Reliance)
ax[1,1].plot(open_prices.index.year,open_prices.Wipro)
plt.show()
I'm playing around with Pandas to see if I can do some stock calculation better/faster than with other tools. If I have a single stock it's easy to create daily calculation L
df['mystuff'] = df['Close']+1
If I download more than a ticker it gets complicated:
df = df.stack()
df['mystuff'] = df['Close']+1
df = df.unstack()
If I want to use prevous' day "Close" it gets too complex for me. I thought I might go back to fetch a single ticker, do any operation with iloc[i-1] or something similar (I haven't figured it yet) and then merge the dataframes.
How do I merget two dataframes of single tickers to have a multiindex?
So that:
f1 = web.DataReader('AAPL', 'yahoo', start, end)
f2 = web.DataReader('GOOG', 'yahoo', start, end)
is like
f = web.DataReader(['AAPL','GOOG'], 'yahoo', start, end)
Edit:
This is the nearest thing to f I can create. It's not exactly the same so I'm not sure I can use it instead of f.
f_f = pd.concat(['AAPL':f1,'GOOG':f2},axis=1)
Maybe I should experiment with operations working on a multiindex instead of splitting work on simpler dataframes.
Full Code:
import pandas_datareader.data as web
import pandas as pd
from datetime import datetime
start = datetime(2001, 9, 1)
end = datetime(2019, 8, 31)
a = web.DataReader('AAPL', 'yahoo', start, end)
g = web.DataReader('GOOG', 'yahoo', start, end)
# here are shift/diff calculations that I don't knokw how to do with a multiindex
a_g = web.DataReader(['AAPL','GOOG'], 'yahoo', start, end)
merged = pd.concat({'AAPL':a,'GOOG':g},axis=1)
a_g.to_csv('ag.csv')
merged.to_csv('merged.csv')
import code; code.interact(local=locals())
side note: I don't know how to compare the two csv
This is not exactly the same but it returns Multiindex you can use as in the a_g case
import pandas_datareader.data as web
import pandas as pd
from datetime import datetime
start = datetime(2019, 7, 1)
end = datetime(2019, 8, 31)
out = []
for tick in ["AAPL", "GOOG"]:
d = web.DataReader(tick, 'yahoo', start, end)
cols = [(col, tick) for col in d.columns]
d.columns = pd.MultiIndex\
.from_tuples(cols,
names=['Attributes', 'Symbols'] )
out.append(d)
df = pd.concat(out, axis=1)
Update
In case you want to calculate and add a new column in case you have multiindex columns you can follow this
import pandas_datareader.data as web
import pandas as pd
from datetime import datetime
start = datetime(2019, 7, 1)
end = datetime(2019, 8, 31)
ticks = ['AAPL','GOOG']
df = web.DataReader(ticks, 'yahoo', start, end)
names = list(df.columns.names)
df1 = df["Close"].shift()
cols = [("New", col) for col in df1.columns]
df1.columns = pd.MultiIndex.from_tuples(cols,
names=names)
df = df.join(df1)
I am trying to plot a histogram but the x ticks does not seem to get right.
The plot is intended to get a histogram of frequency counts ( 1 to 13 ) and total rows in 10000.
d1 = []
for i in np.arange(1, 10000):
tmp = np.random.randint(1, 13)
d1.append(tmp)
d2 = pd.DataFrame(d1)
d2.hist(width = 0.5)
plt.xticks(np.arange(1, 14, 1))
I am trying to plot frequency count of values and not ranges.
You would need to set the bin edges which should be used by the histogram.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
d1 = np.random.randint(1, 13, size=1000)
d2 = pd.DataFrame(d1)
bins = np.arange(0,13)+0.5
d2.hist(bins=bins, ec ="k")
plt.xticks(np.arange(1, 13))
plt.show()