pandas cumsum on lag-differenced dataframe - python

Say I have a pd.DataFrame() that I differenced with .diff(5), which works like "new number at idx i = (number at idx i) - (number at idx i-5)"
import pandas as pd
import random
example_df = pd.DataFrame(data=random.sample(range(1, 100), 20), columns=["number"])
df_diff = example_df.diff(5)
Now I want to undo this operation using the first 5 entries of example_df, and using df_diff.
If i had done .diff(1), I would simply use .cumsum(). But how can I achieve that it only sums up every 5th value?
My desired output is a df with the following values:
df_example[0]
df_example[1]
df_example[2]
df_example[3]
df_example[4]
df_diff[5] + df_example[0]
df_diff[6] + df_example[1]
df_diff[7] + df_example[2]
df_diff[8] + df_example[3]
...

you could shift the column, add them and fill nans:
df_diff["shifted"] = example_df.shift(5)
df_diff["undone"] = df_diff["number"] + df_diff["shifted"]
df_diff["undone"] = df_diff["undone"].fillna(example_df["number"])

Related

Remove non numeric rows from dataframe

I have a dataframe of patients and their gene expressions. I has this format:
Patient_ID | gene1 | gene2 | ... | gene10000
p1 0.142 0.233 ... bla
p2 0.243 0.243 ... -0.364
...
p4000 1.423 bla ... -1.222
As you see, that dataframe contains noise, with cells that are values other then a float value.
I want to remove every row that has a any column with non numeric values.
I've managed to do this using apply and pd.to_numeric like this:
cols = df.columns[1:]
df[cols] = df[cols].apply(pd.to_numeric, errors='coerce')
df = df.dropna()
The problem is that it's taking for ever to run, and I need a better and more efficient way of achieving this
EDIT: To reproduce something like my data:
arr = np.random.random_sample((3000,10000))
df = pd.DataFrame(arr, columns=['gene' + str(i) for i in range(10000)])
df = pd.concat([pd.DataFrame(['p' + str(i) for i in range(10000)], columns=['Patient_ID']),df],axis = 1)
df['gene0'][2] = 'bla'
df['gene9998'][4] = 'bla'
Was right it is worth trying numpy :)
I got 30-60x times faster version (bigger array, larger improvement)
Convert to numpy array (.values)
Iterate through all rows
Try to convert each row to row of floats
If it fails (some NaN present), note this in boolean array
Create array based on the results
Code:
import pandas as pd
import numpy as np
from line_profiler_pycharm import profile
def op_version(df):
cols = df.columns[1:]
df[cols] = df[cols].apply(pd.to_numeric, errors='coerce')
return df.dropna()
def np_version(df):
keep = np.full(len(df), True)
for idx, row in enumerate(df.values[:, 1:]):
try:
row.astype(np.float)
except:
keep[idx] = False
pass # maybe its better to store to_remove list, depends on data
return df[keep]
#profile
def main():
arr = np.random.random_sample((3000, 5000))
df = pd.DataFrame(arr, columns=['gene' + str(i) for i in range(5000)])
df = pd.concat([pd.DataFrame(['p' + str(i) for i in range(3000)],
columns=['Patient_ID']), df], axis=1)
df['gene0'][2] = 'bla'
df['gene998'][4] = 'bla'
df2 = df.copy()
df = op_version(df)
df2 = np_version(df2)
Note I decreased number of columns so it is more feasible for tests.
Also, fixed small bug in your example, instead of:
df = pd.concat([pd.DataFrame(['p' + str(i) for i in range(10000)], columns=['Patient_ID']),df],axis = 1)
I think should be
df = pd.concat([pd.DataFrame(['p' + str(i) for i in range(3000)], columns=['Patient_ID']),df],axis = 1)

Find minima and maxima of DataFrame by chronological order

I have a pandas data frame where I extract minima and extrema values. It work good so far, but the problem is how can I place them by Date (chronological order) into a list? They are separated into two list and I only want one price values list with them being in chronological order
import pandas as pd
import numpy as np
import yfinance
from scipy.signal import argrelextrema
import matplotlib.dates as mpl_dates
def extract_data():
ticker = 'GBPJPY=X'
ticker = yfinance.Ticker(ticker)
start_date = '2022-09-25'
end_date = '2022-10-08'
df = ticker.history(interval='1h', start=start_date, end=end_date)
df['Date'] = pd.to_datetime(df.index)
df['Date'] = df['Date'].apply(mpl_dates.date2num)
df = df.loc[:, ['Date', 'Open', 'High', 'Low', 'Close']]
# Call function to find Min-Max Extrema
find_extrema(df)
def find_extrema(df):
n = 10 # number of points to be checked before and after
# Find local peaks
df['min'] = df.iloc[argrelextrema(df.Close.values, np.less_equal,
order=n)[0]]['Close']
df['max'] = df.iloc[argrelextrema(df.Close.values, np.greater_equal,
order=n)[0]]['Close']
min_values_list = []
max_values_list = []
# Add min value to list
for item in df['min']:
check_NaN = np.isnan(item) # check if values is empty
if check_NaN == True:
pass
else:
min_values_list.append(item)
# Add max values to list
for item in df['max']:
check_NaN = np.isnan(item) # check if values is empty
if check_NaN == True:
pass
else:
max_values_list.append(item)
print(f"Min: {min_values_list}")
print(f"Max: {max_values_list}")
extract_data()
Option 1
First, use df.to_numpy to convert columns min and max to a np.array.
Get rid of all the NaN values by selecting from the array using np.logical_or applied to a boolean mask (created with np.isnan).
arr = df[['min','max']].to_numpy()
value_list = arr[np.logical_not(np.isnan(arr))].tolist()
print(value_list)
[159.7030029296875,
154.8979949951172,
160.7830047607422,
165.43800354003906,
149.55799865722656,
162.80499267578125,
156.6529998779297,
164.31900024414062,
156.125,
153.13499450683594,
161.3520050048828,
156.9340057373047,
162.52200317382812,
155.7740020751953,
160.98500061035156,
161.83700561523438]
Option 2
Rather more cumbersome:
n = 10
# get the indices for `min` and `max` in two arrays
_min = argrelextrema(df.Close.values, np.less_equal, order=n)[0]
_max = argrelextrema(df.Close.values, np.greater_equal, order=n)[0]
# create columns (assuming you need this for other purposes as well)
df['min'] = df.iloc[_min]['Close']
df['max'] = df.iloc[_max]['Close']
# create lists for `min` and `max`
min_values_list = df['min'].dropna().tolist()
max_values_list = df['max'].dropna().tolist()
# join the lists
value_list2 = min_values_list + max_values_list
value_idxs = _min.tolist() + _max.tolist()
# finally, sort `value_list2` based on `value_idxs`
value_list2 = [x for _, x in sorted(zip(value_idxs, value_list2))]
# check if result is the same:
value_list2 == value_list
# True
Assuming that you have max and min columns, what about something like this?
df['max_or_min'] = np.where(df['max'].notna(), df['max'], df['min'])
min_max_values = df['max_or_min'].dropna().values.tolist()

Concatenate on specific condition python

EDITED
I want to write an If loop with conditions on cooncatenating strings.
i.e. If cell A1 contains a specific format of text, then only do you concatenate, else leave as is.
example:
If bill number looks like: CM2/0000/, then concatenate this string with the date column (month - year), else leave the bill number as it is.
Sample Data
You can create function which does what you need and use df.apply() to execute it on all rows.
I use example data from #Boomer answer.
EDIT: you didn't show what you really have in dataframe and it seems you have datetime in bill_date but I used strings. I had to convert strings to datetime to show how to work with this. And now it needs .strftime('%m-%y') or sometimes .dt.strftime('%m-%y') instead of .str[3:].str.replace('/','-'). Because pandas uses different formats to display dateitm for different countries so I couldn't use str(x) for this because it gives me 2019-09-15 00:00:00 instead of yours 15/09/19
import pandas as pd
df = pd.DataFrame({
'bill_number': ['CM2/0000/', 'CM2/0000', 'CM3/0000/', 'CM3/0000'],
'bill_date': ['15/09/19', '15/09/19', '15/09/19', '15/09/19']
})
df['bill_date'] = pd.to_datetime(df['bill_date'])
def convert(row):
if row['bill_number'].endswith('/'):
#return row['bill_number'] + row['bill_date'].str[3:].replace('/','-')
return row['bill_number'] + row['bill_date'].strftime('%m-%y')
else:
return row['bill_number']
df['bill_number'] = df.apply(convert, axis=1)
print(df)
Result:
bill_number bill_date
0 CM2/0000/09-19 15/09/19
1 CM2/0000 15/09/19
2 CM3/0000/09-19 15/09/19
3 CM3/0000 15/09/19
Second idea is to create mask
mask = df['bill_number'].str.endswith('/')
and later use it for all values
#df.loc[mask,'bill_number'] = df[mask]['bill_number'] + df[mask]['bill_date'].str[3:].str.replace('/','-')
df.loc[mask,'bill_number'] = df[mask]['bill_number'] + df[mask]['bill_date'].dt.strftime('%m-%y')
or
#df.loc[mask,'bill_number'] = df.loc[mask,'bill_number'] + df.loc[mask,'bill_date'].str[3:].str.replace('/','-')
df.loc[mask,'bill_number'] = df.loc[mask,'bill_number'] + df.loc[mask,'bill_date'].dt.strftime('%m-%y')
Left side needs .loc[mask,'bill_number'] instead of `[mask]['bill_number'] to correctly assing values - but right side doesn't need it.
import pandas as pd
df = pd.DataFrame({
'bill_number': ['CM2/0000/', 'CM2/0000', 'CM3/0000/', 'CM3/0000'],
'bill_date': ['15/09/19', '15/09/19', '15/09/19', '15/09/19']
})
df['bill_date'] = pd.to_datetime(df['bill_date'])
mask = df['bill_number'].str.endswith('/')
#df.loc[mask,'bill_number'] = df[mask]['bill_number'] + df[mask]['bill_date'].str[3:].str.replace('/','-')
# or
#df.loc[mask,'bill_number'] = df.loc[mask,'bill_number'] + df.loc[mask,'bill_date'].str[3:].str.replace('/','-')
df.loc[mask,'bill_number'] = df[mask]['bill_number'] + df[mask]['bill_date'].dt.strftime('%m-%y')
#or
#df.loc[mask,'bill_number'] = df.loc[mask,'bill_number'] + df.loc[mask,'bill_date'].dt.strftime('%m-%y')
print(df)
Third idea is to use numpy.where()
import pandas as pd
import numpy as np
df = pd.DataFrame({
'bill_number': ['CM2/0000/', 'CM2/0000', 'CM3/0000/', 'CM3/0000'],
'bill_date': ['15/09/19', '15/09/19', '15/09/19', '15/09/19']
})
df['bill_date'] = pd.to_datetime(df['bill_date'])
df['bill_number'] = np.where(
df['bill_number'].str.endswith('/'),
#df['bill_number'] + df['bill_date'].str[3:].str.replace('/','-'),
df['bill_number'] + df['bill_date'].dt.strftime('%m-%y'),
df['bill_number'])
print(df)
Maybe this will work for you. It would be nice to have a data sample like #Mike67 was stating. But based on your information this is what I came up with. Bulky, but it works. I'm sure someone else will have a fancier version.
import pandas as pd
from pandas import DataFrame, Series
dat = {'num': ['CM2/0000/','CM2/0000', 'CM3/0000/', 'CM3/0000',],
'date': ['15/09/19','15/09/19','15/09/19','15/09/19']}
df = pd.DataFrame(dat)
df['date'] = df['date'].map(lambda x: str(x)[3:])
df['date'] = df['date'].str.replace('/','-')
for cols in df.columns:
df.loc[df['num'].str.endswith('/'), cols] = df['num'] + df['date']
print(df)
Results:
num date
0 CM2/0000/09-19 09-19
1 CM2/0000 09-19
2 CM3/0000/09-19 09-19
3 CM3/0000 09-19

How to add some calculation in columns of the dataframe in python

I am having the excel sheet using the pandas.read_excel, I got the output in dataframe but I want to add the calculations in the after reading through pandas I need to ado following calculation in each x and y columns.
ratiox = (73.77481944859028 - 73.7709567323327) / 720
ratioy = (18.567453940477293 - 18.56167674097576) / 1184
mapLongitudeStart = 73.7709567323327
mapLatitudeStart = 18.567453940477293
longitude = 0, latitude = 0
longitude = (mapLongitudeStart + x1 * ratiox)) #I have take for the single column x1 value
latitude = (mapLatitudeStart - (-y1 *ratioy )) # taken column y1 value
how to apply this calculation to every column and row of x and y a which has the values it should not take the null values. And I want the new dataframe created by doing the calculation in columns
Try the below code:
import pandas as pd
import itertools
df = pd.read_excel('file_path')
dfx=df.ix[:,'x1'::2]
dfy=df.ix[:,'y1'::2]
li=[dfx.apply(lambda x:mapLongitudeStart + x * ratiox),dfy.apply(lambda y:mapLatitudeStart - (-y))]
df_new=pd.concat(li,axis=1)
df_new = df_new[list(itertools.chain(*zip(dfx.columns,dfy.columns)))]
print(df_new)
Hope this helps!
I would first recommend to reshape your data into a long format, that way you can get rid of the empty cells naturally. Also most pandas functions work better that way, because then you can use things like group by operations on all x or y or wahtever dimenstion
from itertools import chain
import pandas as pd
## this part is only to have a running example
## here you would load your excel file
D = pd.DataFrame(
np.random.randn(10,6),
columns =chain(*[ [f"x{i}", f"y{i}"] for i in range(1,4)])
)
D["rowid"] = pd.np.arange(len(D))
D = D.melt(id_vars="rowid").dropna()
D["varIndex"] = D.variable.str[1]
D["variable"] = D.variable.str[0]
D = D.set_index(["varIndex","rowid","variable"])\
.unstack("variable")\
.droplevel(0, axis=1)
So these transformations will give you a table where you have an index both for the original row id (maybe it is a time series or something else), and the variable index so x1 or x2 etc.
Now you can do your calculations either by overwintering the previous columns
## Everything here is a constant
ratiox = (73.77481944859028 - 73.7709567323327) / 720
ratioy = (18.567453940477293 - 18.56167674097576) / 1184
mapLongitudeStart = 73.7709567323327
mapLatitudeStart = 18.567453940477293
# apply the calculations directly to the columns
D.x = (mapLongitudeStart + D.x * ratiox))
D.y = (mapLatitudeStart - (-D.y * ratioy ))

How to fill missing date in timeSeries

Here's what my data looks like:
There are daily records, except for a gap from 2017-06-12 to 2017-06-16.
df2['timestamp'] = pd.to_datetime(df['timestamp'])
df2['timestamp'] = df2['timestamp'].map(lambda x:
datetime.datetime.strftime(x,'%Y-%m-%d'))
df2 = df2.convert_objects(convert_numeric = True)
df2 = df2.groupby('timestamp', as_index = False).sum()
I need to fill this missing gap and others with values for all fields (e.g. timestamp, temperature, humidity, light, pressure, speed, battery_voltage, etc...).
How can I accomplish this with Pandas?
This is what I have done before
weektime = pd.date_range(start = '06/04/2017', end = '12/05/2017', freq = 'W-SUN')
df['week'] = 'nan'
df['weektemp'] = 'nan'
df['weekhumidity'] = 'nan'
df['weeklight'] = 'nan'
df['weekpressure'] = 'nan'
df['weekspeed'] = 'nan'
df['weekbattery_voltage'] = 'nan'
for i in range(0,len(weektime)):
df['week'][i+1] = weektime[i]
df['weektemp'][i+1] = df['temperature'].iloc[7*i+1:7*i+7].sum()
df['weekhumidity'][i+1] = df['humidity'].iloc[7*i+1:7*i+7].sum()
df['weeklight'][i+1] = df['light'].iloc[7*i+1:7*i+7].sum()
df['weekpressure'][i+1] = df['pressure'].iloc[7*i+1:7*i+7].sum()
df['weekspeed'][i+1] = df['speed'].iloc[7*i+1:7*i+7].sum()
df['weekbattery_voltage'][i+1] =
df['battery_voltage'].iloc[7*i+1:7*i+7].sum()
i = i + 1
The value of sum is not correct. Cause the value of 2017-06-17 is a sum of 2017-06-12 to 2017-06-16. I do not want to add them again. This gap is not only one gap in the period. I want to fill all of them.
Here is a function I wrote that might be helpful to you. It looks for inconsistent jumps in time and fills them in. After using this function, try using a linear interpolation function (pandas has a good one) to fill in your null data values. Note: Numpy arrays are much faster to iterate over and manipulate than Pandas dataframes, which is why I switch between the two.
import numpy as np
import pandas as pd
data_arr = np.array(your_df)
periodicity = 'daily'
def fill_gaps(data_arr, periodicity):
rows = data_arr.shape[0]
data_no_gaps = np.copy(data_arr) #avoid altering the thing you're iterating over
data_no_gaps_idx = 0
for row_idx in np.arange(1, rows): #iterate once for each row (except the first record; nothing to compare)
oldtimestamp_str = str(data_arr[row_idx-1, 0])
oldtimestamp = np.datetime64(oldtimestamp_str)
currenttimestamp_str = str(data_arr[row_idx, 0])
currenttimestamp = np.datetime64(currenttimestamp_str)
period = currenttimestamp - oldtimestamp
if period != np.timedelta64(900,'s') and period != np.timedelta64(3600,'s') and period != np.timedelta64(86400,'s'):
if periodicity == 'quarterly':
desired_period = 900
elif periodicity == 'hourly':
desired_period = 3600
elif periodicity == 'daily':
desired_period = 86400
periods_missing = int(period / np.timedelta64(desired_period,'s'))
for missing in np.arange(1, periods_missing):
new_time_orig = str(oldtimestamp + missing*(np.timedelta64(desired_period,'s')))
new_time = new_time_orig.replace('T', ' ')
data_no_gaps = np.insert(data_no_gaps, (data_no_gaps_idx + missing),
np.array((new_time, np.nan, np.nan, np.nan, np.nan, np.nan)), 0) # INSERT VALUES YOU WANT IN THE NEW ROW
data_no_gaps_idx += (periods_missing-1) #incriment the index (zero-based => -1) in accordance with added rows
data_no_gaps_idx += 1 #allow index to change as we iterate over original data array (main for loop)
#create a dataframe:
data_arr_no_gaps = pd.DataFrame(data=data_no_gaps, index=None,columns=['Time', 'temp', 'humidity', 'light', 'pressure', 'speed'])
return data_arr_no_gaps
Fill time gaps and nulls
Use the function below to ensure expected date sequence exists, and then use forward fill to fill in nulls.
import pandas as pd
import os
def fill_gaps_and_nulls(df, freq='1D'):
'''
General steps:
A) check for extra dates (out of expected frequency/sequence)
B) check for missing dates (based on expected frequency/sequence)
C) use forwardfill to fill nulls
D) use backwardfill to fill remaining nulls
E) append to file
'''
#rename the timestamp to 'date'
df.rename(columns={"timestamp": "date"})
#sort to make indexing faster
df = df.sort_values(by=['date'], inplace=False)
#create an artificial index of dates at frequency = freq, with the same beginning and ending as the original data
all_dates = pd.date_range(start=df.date.min(), end=df.date.max(), freq=freq)
#record column names
df_cols = df.columns
#delete ffill_df.csv so we can begin anew
try:
os.remove('ffill_df.csv')
except FileNotFoundError:
pass
#check for extra dates and/or dates out of order. print warning statement for log
extra_dates = set(df.date).difference(all_dates)
#if there are extra dates (outside of expected sequence/frequency), deal with them
if len(extra_dates) > 0:
#############################
#INSERT DESIRED BEHAVIOR HERE
print('WARNING: Extra date(s):\n\t{}\n\t Shifting highlighted date(s) back by 1 day'.format(extra_dates))
for date in extra_dates:
#shift extra dates back one day
df.date[df.date == date] = date - pd.Timedelta(days=1)
#############################
#check the artificial date index against df to identify missing gaps in time and fill them with nulls
gaps = all_dates.difference(set(df.date))
print('\n-------\nWARNING: Missing dates: {}\n-------\n'.format(gaps))
#if there are time gaps, deal with them
if len(gaps) > 0:
#initialize df of correct size, filled with nulls
gaps_df = pd.DataFrame(index=gaps, columns=df_cols.drop('date')) #len(index) sets number of rows
#give index a name
gaps_df.index.name = 'date'
#add the region and type
gaps_df.region = r
gaps_df.type = t
#remove that index so gaps_df and df are compatible
gaps_df.reset_index(inplace=True)
#append gaps_df to df
new_df = pd.concat([df, gaps_df])
#sort on date
new_df.sort_values(by='date', inplace=True)
#fill nulls
new_df.fillna(method='ffill', inplace=True)
new_df.fillna(method='bfill', inplace=True)
#append to file
new_df.to_csv('ffill_df.csv', mode='a', header=False, index=False)
return df_cols, regions, types, all_dates

Categories