I tried to follow what was suggested here. But it seems that only a few columns get effected when I tried either of the following functions:
def get_col_widths(dataframe):
# First we find the maximum length of the index column
idx_max = max([len(str(s)) for s in dataframe.index.values] + [len(str(dataframe.index.name))])
# Then, we concatenate this to the max of the lengths of column name and its values for each column, left to right
return [idx_max] + [max([len(str(s)) for s in dataframe[col].values] + [len(col)]) for col in dataframe.columns]
for i, width in enumerate(get_col_widths(df)):
worksheet.set_column(i, i, width)
def set_column_width(df):
length_list = [len(x) for x in df.columns]
for i, width in enumerate(length_list):
worksheet.set_column(i, i, width)
I may not be using the functions above correctly. Thus here is my entire code:
import openpyxl
import sql_utils as sql
from datetime import date
from datetime import timedelta
from dateutil.relativedelta import relativedelta
from pandas.tseries.holiday import USFederalHolidayCalendar
import pyodbc
import pandas as pd
import datetime
import numpy as np
import xlsxwriter
from openpyxl import load_workbook
import sys
import win32com.client as win32
from win32com.client import Dispatch
cal = USFederalHolidayCalendar()
# pylint: disable=no-member
cnxn = pyodbc.connect(sql.connection_string)
# Set dates for the queries
cutoff_date = datetime.date(2019, 6, 30)
output_file = ".\\pa-jpm-reporting\\output\\jpm_morgans_report.xlsx"
if len(sys.argv) > 1:
cutoff_date = datetime.datetime.strptime(sys.argv[1], '%Y-%m-%d').date()
output_file = sys.argv[2]
writer = pd.ExcelWriter(output_file)
def get_first_business_day_of_month(start_date, end_date):
return [
get_business_day(d).date()
for d in pd.date_range(start_date, end_date, freq="BMS")
]
def get_business_day(date):
while date.isoweekday() > 5 or date in cal.holidays():
date += timedelta(days=1)
return date
# Get as_of_date and archive_date
archive_date = get_first_business_day_of_month(cutoff_date, cutoff_date + relativedelta(days=+10))[0]
as_of_date = datetime.date(archive_date.year, 1, 1)
# Pull date
def get_sql(cutoff_date, archive_date, as_of_date):
return sql.jpm_rate_query.format(cutoff_date, archive_date, as_of_date)
def get_sql2(utoff_date, archive_date, as_of_date):
return sql.jpm_query.format(cutoff_date, archive_date, as_of_date)
# Get data into a pandas dataframe
def get_dataframe(cutoff_date, archive_date, as_of_date):
cnxn.execute(get_sql(cutoff_date, archive_date, as_of_date))
data = pd.read_sql(get_sql2(cutoff_date, archive_date, as_of_date), cnxn)
return data
df = get_dataframe(cutoff_date, archive_date, as_of_date)
df['ModEffectiveDate'] = pd.to_datetime(df['ModEffectiveDate'])
df['StepDate1'] = pd.to_datetime(df['StepDate1'])
# Fix step date
def date_check(date1, date2):
if date1 > date2:
return 'X'
else:
return ' '
df['Step date prior to mod'] = df.apply(lambda x: date_check(x['ModEffectiveDate'], x['StepDate1']), axis=1)
# Fix step check
cols = df.filter(regex='StepRate').columns
df['Later Step Rate not higher than previous'] = ' '
for i, col in enumerate(cols):
if i <= len(cols) - 2:
df['Later Step Rate not higher than previous'] = np.where(df[col] > df[cols[i+1]],'X',df['Later Step Rate not higher than previous'])
else:
break
# Format the Dates
df['CutoffDate'].astype('datetime64[ns]')
df['CutoffDate'] = pd.to_datetime(df['CutoffDate']).dt.strftime("%m/%d/%Y")
df['ModEffectiveDate'].astype('datetime64[ns]')
df['ModEffectiveDate'] = pd.to_datetime(df['ModEffectiveDate']).dt.strftime("%m/%d/%Y")
df['StepDate1'].astype('datetime64[ns]')
df['StepDate1'] = pd.to_datetime(df['StepDate1']).dt.strftime("%m/%d/%Y")
df = df.replace('NaT', '', regex=True)
# clean up (remove) zero step rates that follow the last true step
cols = df.filter(regex='StepRate').columns
for i, col in enumerate(cols):
df[col] = df[col].replace(0, '', regex=True)
# remove repeated loan number shown immediately before the step dates
df = df.drop(['loanid'], axis=1)
# Add color to column
def highlight(s):
same = s == df['CutoffDate']
return ['background-color: lightblue' if x else '' for x in same]
df.style.highlight_null(null_color='green')
df.to_excel(writer, index=False)
workbook = writer.book
worksheet = writer.sheets['Sheet1']
# Freeze 1st row
worksheet.freeze_panes(1,0)
# Place dollar amounts where relevant
num_format = workbook.add_format({'num_format': '#,##0.00'})
# Find the columns (numbers) with float64 type and set the number format
nametypemap = df.dtypes.apply(lambda x: x.name).to_dict()
for i, (k, v) in enumerate(nametypemap.items()):
# print("index: {}, key: {}, value: {}".format(i, k, v))
if v == 'float64':
worksheet.set_column(i, i, 12, num_format)
def get_col_widths(dataframe):
# First we find the maximum length of the index column
idx_max = max([len(str(s)) for s in dataframe.index.values] + [len(str(dataframe.index.name))])
# Then, we concatenate this to the max of the lengths of column name and its values for each column, left to right
return [idx_max] + [max([len(str(s)) for s in dataframe[col].values] + [len(col)]) for col in dataframe.columns]
for i, width in enumerate(get_col_widths(df)):
worksheet.set_column(i, i, width)
def set_column_width(df):
length_list = [len(x) for x in df.columns]
for i, width in enumerate(length_list):
worksheet.set_column(i, i, width)
set_column_width(df)
writer.save()
Please let me know if there is a way of doing this. I am also having a hard time trying to highlight a column in the dataframe. But I will make another separate post for that.
Related
import pandas as pd
l1 = ["2021-11-15","2021-11-13","2021-11-10","2021-05-28","2021-06-02","2021-06-02","2021-11-02"]
l2 = ["2021-11-11","2021-03-02","2021-11-05","2021-05-20","2021-05-01","2021-06-01","2021-04-08"]
#convert to dt
l1=pd.to_datetime(l1)
l2= pd.to_datetime(l2)
#put in df
df1=pd.DataFrame(l1)
df2=pd.DataFrame(l2)
df1.columns = ['0']
df2.columns = ['0']
df1=df1.set_index('0')
df2=df2.set_index('0')
#sort asc
df1=df1.sort_index()
df2=df2.sort_index()
How can I get a COUNT from each dataframe based on the number of rows that are within the last 7 days?
you can slice between two timestamps and then get the number of rows with .shape[0]:
def get_count_last_7_days(df):
stop = df.index.max()
start = stop - pd.Timedelta('7D')
return df.loc[start:stop].shape[0]
count1 = get_count_last_7_days(df1)
count2 = get_count_last_7_days(df2)
import pandas as pd
import numpy as np
from datetime import date, timedelta
x = (date.today() - timedelta(days=100))
y = (date.today() - timedelta(days=7))
z = date.today()
dates = pd.date_range(x, periods=100)
d = np.arange(1, 101)
df = pd.DataFrame(data=d, index=pd.DatetimeIndex(dates))
df = df.sort_index()
last_seven_days = df.loc[y:z]
print(last_seven_days.count())
Your last 7 days is ambiguous, I assume it's calculated from current time:
today = datetime.today()
week_ago = today - timedelta(days=7)
Since you already set the date as index, you can use .loc directly, but you also can use a mask:
df = df1.loc[week_ago:today]
# or
df = df1[(df1.index > week_ago) & (df1.index < today)]
To get row count, you can use shape accessor or sum the boolean mask
count = df1.loc[week_ago:today].shape[0]
# or
sum((df1.index > week_ago) & (df1.index < today))
I am new to Pandas, and I'm trying to avoid iterating over a DataFrame, and attempting to use vectorisation instead. I am not able to get the results I want; I need help in the more complicated masking and selection statements
This is my code:
import random
from datetime import datetime, timedelta
import pandas as pd
dates = []
temp = []
press = []
vel = []
fmt = '%Y-%m-%d %H:%M:%S'
stime = datetime.strptime('2020-01-06 10:28:16', fmt)
etime = datetime.strptime('2020-04-10 03:43:12', fmt)
td = etime - stime
l = set([random.random() for x in range(0, 1000)])
dates = [((td * x) + stime) for x in random.sample(l, 100)]
for i in range(100):
press.append(random.uniform(14,95.5))
temp.append(random.uniform(-15,45))
vel.append(random.uniform(50,153))
measurements = {
'date' : dates,
'pressure' : press,
'velocity' : vel,
'temperature': temp
}
df = pd.DataFrame(measurements)
df['date'] = pd.to_datetime(df['date'])
df.set_index('date', inplace=True)
df = df.sort_index()
df2 = pd.DataFrame()
# if temp increased from previous row, set flag
df2['temp_inc'] = df['temperature'] - df.shift(1)['temperature'] > 0
df2['temp_inc'] = df2['temp_inc'].replace({True: 1, False: 0})
# need to fetch velocity where pressure has increased from previous row, else 0
press_up_mask = df.where( (df['pressure'] - df.shift(1)['pressure']) > 0)
#df2['press_spike_velocity'] = df[press_up_mask]['velocity']
# Need to perform calc based on 'temp_inc' column: if 'temp_inc' column is 1: calculate pressure * velocity, else 0
temp_inc_mask = df2['temp_inc'] == 1
df2['boyle_fact'] = df[temp_inc_mask]['pressure'] * df[temp_inc_mask]['velocity']
# Get some stats
df2['short_max_temp'] = df['temperature'].rolling(3).max()
df2['long_min_pressure'] = df['pressure'].rolling(30).min()
print(df.head())
print(df2.head())
How do I correctly calculate columns 'press_spike_velocity' and 'boyle_fact' ?
Starting from the computations:
# if temp increased from previous row, set flag
df2['temp_inc'] = df['temperature'] - df.shift(1)['temperature'] > 0
# setting int type instead of replace
df2['temp_inc'] = df2['temp_inc'].astype(int)
# need to fetch velocity where pressure has increased from previous row, else 0
press_up_mask = df.where( (df['pressure'] - df['pressure'].shift(1)) > 0)
# set column to velocity then mask in zeros via assignment
df2['press_spike_velocity'] = df['velocity'].copy()
df2['press_spike_velocity'][~press_up_mask] = 0
# Need to perform calc based on 'temp_inc' column: if 'temp_inc' column is 1: calculate pressure * velocity, else 0
temp_inc_mask = df2['temp_inc'] == 1
# same masking approach as above
df2['boyle_fact'] = df['pressure'] * df['velocity']
df2['boyle_fact'][~temp_inc_mask] = 0
This is the simplest way to solve your problem with minimal changes to the code itself. If you dig into pandas more you could probably find methods to do this in 1-2 fewer lines via inplace operations but I don't know how much performance or readability you would gain from that.
i have a dataframe like this
id_1,date_1,id_2,date_2
I need dataframe where rows (date_1 + 15 days) < date_2
in case where this rule is match I need only first occurence
Just using boolean mask is not solve the problem
So I think may be I need to use
some kind offor index, row in df.iterrows():
and create new dataframe
import pandas as pd
from datetime import timedelta
df = pd.DataFrame(data=dd)
df[['date_1', 'date_2']] = df[['date_1', 'date_2']].apply(pd.to_datetime)
df['date_1_15'] = df['date_1'] + timedelta(4)
def apply_mask(row):
if row['date_1_15'] < row['date_2']:
row['mask'] = True
else:
row['mask'] = False
return row
df = df.apply(lambda row: apply_mask(row), axis=1)
dx = df.loc[df['mask'] == True]
dx = dx.groupby(['date_1']).first()
dx['mask_first'] = True
dx = dx.reset_index()
dx = dx[['date_1', 'date_2', 'mask_first']]
df = pd.merge(df, dx, on=['date_1', 'date_2'], how='outer')
import pandas as pd
from datetime import timedelta
df = pd.DataFrame(data={'id_1':[1,2,3,4],
'date1': ['2018-01-10', '2018-02-05', '2018-02-20', '2018-02-21'],
'date2': ['2018-01-11', '2018-02-15', '2018-02-27', '2018-02-22']})
df[['date1', 'date2']] = df[['date1', 'date2']].apply(pd.to_datetime)
df['date1_15'] = df['date1'] + timedelta(15)
df = df.loc[df['date1_15'] < df['date2']].head(1)
I want to create a function that will read a series of time values from a file (with gaps in the sampling rate,thats the problem) and would read me exactly 200 days and allow me to move through the entire data length,say 10000 day,sort of a rolling window.
I am not sure how to code it. Can I add a statement that calculates the difference between two values of the time variable (x axis) up to when is exactly 200 days?
Or can I somehow write a function that would find the starting value say t0 and then find the element of the array that is closest to t0 + (interval=) 200 days.
What I have so far is:
f = open(reading the file from directory)
lines = f.readlines()
print(len(lines))
tx = np.array([]) # times
y= np.array([])
interval = 200 # days
for li in lines:
col = li.split()
t0 = np.array([])
t1 = np.array([])
tx = np.append(tx, float(col[0]))
y= np.append(y, float(col[1]))
t0 = np.append(t0, np.max(tx))
t1 = np.append(t1, tx[np.argmin(tx)])
print(t0,t1)
days = [t1 + dt.timedelta(days = float(x)) for x in days]
#y = np.random.randn(len(days))
# use pandas for convenient rolling function:
df = pd.DataFrame({"day":tx, "value": y}).set_index("day")
def closest_value(s):
if s.shape[0]<2:
return np.nan
X = np.empty((s.shape[0]-1, 2))
X[:, 0] = s[:-1]
X[:, 1] = np.fabs(s[:-1]-s[-1])
min_diff = np.min(X[:, 1])
return X[X[:, 1]==min_diff, 0][0]
df['closest_value'] = df.rolling(window=dt.timedelta(days=200))
['value'].apply(closest_value, raw=True)
print(df.tail(5))
Output error:
TypeError: float() argument must be a string or a number, not
'datetime.datetime'
Additionally,
First 10 tx and ty values respectively:
0 0.003372722575018
0.015239999629557 0.003366515509113
0.045829999726266 0.003385171061055
0.075369999743998 0.003385171061055
0.993219999596477 0.003366515509113
1.022699999623 0.003378941085299
1.05217999964952 0.003369617612836
1.08166999975219 0.003397665493594
3.0025899996981 0.003378941085299
3.04120999993756 0.003394537568711
import numpy as np
import pandas as pd
import datetime as dt
# load data in days and y arrays
# ... or generate them:
N = 1000 # number of days
day_min = dt.datetime.strptime('2000-01-01', '%Y-%m-%d')
day_max = 2000
days = np.sort(np.unique(np.random.uniform(low=0, high=day_max, size=N).astype(int)))
days = [day_min + dt.timedelta(days = int(x)) for x in days]
y = np.random.randn(len(days))
# use pandas for convenient rolling function:
df = pd.DataFrame({"day":days, "value": y}).set_index("day")
def closest_value(s):
if s.shape[0]<2:
return np.nan
X = np.empty((s.shape[0]-1, 2))
X[:, 0] = s[:-1]
X[:, 1] = np.fabs(s[:-1]-s[-1])
min_diff = np.min(X[:, 1])
return X[X[:, 1]==min_diff, 0][0]
df['closest_value'] = df.rolling(window=dt.timedelta(days=200))['value'].apply(closest_value, raw=True)
print(df.tail(5))
Output:
value closest_value
day
2005-06-15 1.668638 1.591505
2005-06-16 0.316645 0.304382
2005-06-17 0.458580 0.445592
2005-06-18 -0.846174 -0.847854
2005-06-22 -0.151687 -0.166404
You could use pandas, set a datetime range and create a while loop to process the data in batches.
import pandas as pd
from datetime import datetime, timedelta
# Load data into pandas dataframe
df = pd.read_csv(filepath)
# Name columns
df.columns = ['dates', 'num_value']
# Convert strings to datetime
df.dates = pd.to_datetime(df['dates'], format='%d/%m/%Y')
# Print dates within a 200 day interval and move on to the next interval
i = 0
while i < len(df.dates):
start = df.dates[i]
end = start + timedelta(days=200)
print(df.dates[(df.dates >= start) & (df.dates < end)])
i += 200
If the columns don't have headers, you should omit skiprows:
dates num_value
2004-7-1 1
2004-7-2 5
2004-7-4 8
2004-7-5 11
2004-7-6 17
df = pd.read_table(filepath, sep="\s+", skiprows=1)
I am trying to pull the logs with respect to time slots. The program below runs very fine when no. of hours are given and the logs in that range gets extracted.
But now I also what to include Start and end to be dynamically given. i.e. say between 8 am to 8pm or 6am to 8am and so on.
How do I get that? Any edit in the current program will also do or a separate program will also do.
Input: Mini Version of INPUT
Code:
import pandas as pd
from datetime import datetime,time
import numpy as np
fn = r'00_Dart.csv'
cols = ['UserID','StartTime','StopTime', 'gps1', 'gps2']
df = pd.read_csv(fn, header=None, names=cols)
df['m'] = df.StopTime + df.StartTime
df['d'] = df.StopTime - df.StartTime
# 'start' and 'end' for the reporting DF: `r`
# which will contain equal intervals (1 hour in this case)
start = pd.to_datetime(df.StartTime.min(), unit='s').date()
end = pd.to_datetime(df.StopTime.max(), unit='s').date() + pd.Timedelta(days=1)
# building reporting DF: `r`
freq = '1H' # 1 Hour frequency
idx = pd.date_range(start, end, freq=freq)
r = pd.DataFrame(index=idx)
r['start'] = (r.index - pd.datetime(1970,1,1)).total_seconds().astype(np.int64)
# 1 hour in seconds, minus one second (so that we will not count it twice)
interval = 60*60 - 1
r['LogCount'] = 0
r['UniqueIDCount'] = 0
for i, row in r.iterrows():
# intervals overlap test
# https://en.wikipedia.org/wiki/Interval_tree#Overlap_test
# i've slightly simplified the calculations of m and d
# by getting rid of division by 2,
# because it can be done eliminating common terms
u = df[np.abs(df.m - 2*row.start - interval) < df.d + interval].UserID
r.ix[i, ['LogCount', 'UniqueIDCount']] = [len(u), u.nunique()]
r['Date'] = pd.to_datetime(r.start, unit='s').dt.date
r['Day'] = pd.to_datetime(r.start, unit='s').dt.weekday_name.str[:3]
r['StartTime'] = pd.to_datetime(r.start, unit='s').dt.time
r['EndTime'] = pd.to_datetime(r.start + interval + 1, unit='s').dt.time
#r.to_csv('results.csv', index=False)
#print(r[r.LogCount > 0])
#print (r['StartTime'], r['EndTime'], r['Day'], r['LogCount'], r['UniqueIDCount'])
rout = r[['Date', 'StartTime', 'EndTime', 'Day', 'LogCount', 'UniqueIDCount'] ]
#print rout
rout.to_csv('one_hour.csv', index=False, header=False)
Edit:
In Simple words, I should be able to give StartTime and EndTIme in the program. The code below is very much close to what I am trying to do. But how convert this to pandas.
from datetime import datetime,time
start = time(8,0,0)
end = time(20,0,0)
with open('USC28days_0_20', 'r') as infile, open('USC28days_0_20_time','w') as outfile:
for row in infile:
col = row.split()
t1 = datetime.fromtimestamp(float(col[2])).time()
t2 = datetime.fromtimestamp(float(col[3])).time()
print (t1 >= start and t2 <= end)
Edit Two: Working answer in Pandas
Taking a Part from the #MaxU's answer from selected answer. The below code strips the required group of logs between the given StartTime and StopTime
import pandas as pd
from datetime import datetime,time
import numpy as np
fn = r'00_Dart.csv'
cols = ['UserID','StartTime','StopTime', 'gps1', 'gps2']
df = pd.read_csv(fn, header=None, names=cols)
#df['m'] = df.StopTime + df.StartTime
#df['d'] = df.StopTime - df.StartTime
# filter input data set ...
start_hour = 8
end_hour = 9
df = df[(pd.to_datetime(df.StartTime, unit='s').dt.hour >= start_hour) & (pd.to_datetime(df.StopTime, unit='s').dt.hour <= end_hour)]
print df
df.to_csv('time_hour.csv', index=False, header=False)
But: If there was a possibility to have control on minutes and seconds also would be great solution.
At present this also strips the logs which have the hour of StopTime but also the minutes and seconds until the next hour.
Something like
start_hour = 8:0:0
end_hour = 9:0:0 - 1 # -1 to get the logs until 8:59:59
But this gives me an error
try this:
import pandas as pd
from datetime import datetime,time
import numpy as np
fn = r'D:\data\gDrive\data\.stack.overflow\2016-07\dart_small.csv'
cols = ['UserID','StartTime','StopTime', 'gps1', 'gps2']
df = pd.read_csv(fn, header=None, names=cols)
df['m'] = df.StopTime + df.StartTime
df['d'] = df.StopTime - df.StartTime
# filter input data set ...
start_hour = 8
end_hour = 20
df = df[(pd.to_datetime(df.StartTime, unit='s').dt.hour >= 8) & (pd.to_datetime(df.StartTime, unit='s').dt.hour <= 20)]
# 'start' and 'end' for the reporting DF: `r`
# which will contain equal intervals (1 hour in this case)
start = pd.to_datetime(df.StartTime.min(), unit='s').date()
end = pd.to_datetime(df.StopTime.max(), unit='s').date() + pd.Timedelta(days=1)
# building reporting DF: `r`
freq = '1H' # 1 Hour frequency
idx = pd.date_range(start, end, freq=freq)
r = pd.DataFrame(index=idx)
r = r[(r.index.hour >= start_hour) & (r.index.hour <= end_hour)]
r['start'] = (r.index - pd.datetime(1970,1,1)).total_seconds().astype(np.int64)
# 1 hour in seconds, minus one second (so that we will not count it twice)
interval = 60*60 - 1
r['LogCount'] = 0
r['UniqueIDCount'] = 0
for i, row in r.iterrows():
# intervals overlap test
# https://en.wikipedia.org/wiki/Interval_tree#Overlap_test
# i've slightly simplified the calculations of m and d
# by getting rid of division by 2,
# because it can be done eliminating common terms
u = df[np.abs(df.m - 2*row.start - interval) < df.d + interval].UserID
r.ix[i, ['LogCount', 'UniqueIDCount']] = [len(u), u.nunique()]
r['Date'] = pd.to_datetime(r.start, unit='s').dt.date
r['Day'] = pd.to_datetime(r.start, unit='s').dt.weekday_name.str[:3]
r['StartTime'] = pd.to_datetime(r.start, unit='s').dt.time
r['EndTime'] = pd.to_datetime(r.start + interval + 1, unit='s').dt.time
#r.to_csv('results.csv', index=False)
#print(r[r.LogCount > 0])
#print (r['StartTime'], r['EndTime'], r['Day'], r['LogCount'], r['UniqueIDCount'])
rout = r[['Date', 'StartTime', 'EndTime', 'Day', 'LogCount', 'UniqueIDCount'] ]
#print rout
OLD answer:
from_time = '08:00'
to_time = '18:00'
rout.between_time(from_time, to_time).to_csv('one_hour.csv', index=False, header=False)