Working with Dates and Times in Python

# Add your code snippets here
# Import datetime
from datetime import datetime

# Create a datetime object
dt = datetime(2017,10,1,15,19,13)

# Print the results in ISO 8601 format
print(dt.isoformat())

# Replace the year with 1917
dt_old = dt.replace(year=1917)

# Print the results in ISO 8601 format
print(dt_old)

# Import the datetime class
from datetime import datetime

# Starting string, in YYYY-MM-DD HH:MM:SS format
s = '2017-02-03 00:00:01'

# Write a format string to parse s
fmt = '%Y-%m-%d %H:%M:%S'

# Create a datetime object d
d = datetime.strptime(s, fmt)

# Print d
print(d)

fmt_iso = "%Y-%m-%dT%H:%M:%S"

# Print out date with .isoformat(), then with .strftime() to compare
print(first_start.isoformat())
print(first_start.strftime(fmt_iso))

# Starting timestamps
timestamps = [1514665153, 1514664543]

# Datetime objects
dts = []

# Loop
for ts in timestamps:
  dts.append(datetime.fromtimestamp(ts))
  
# Print results
print(dts)

# Initialize a list for all the trip durations
onebike_durations = []

for trip in onebike_datetimes:
  # Create a timedelta object corresponding to the length of the trip
  trip_duration = trip['end'] - trip['start']
  
  # Get the total elapsed seconds in trip_duration
  trip_length_seconds = trip_duration.total_seconds()
  
  # Append the results to our list
  onebike_durations.append(trip_length_seconds)

# Import datetime, timedelta, timezone
from datetime import datetime, timedelta, timezone

# Create a timezone for Pacific Standard Time, or UTC-8
pst = timezone(timedelta(hours=5))

# October 1, 2017 at 15:26:26, UTC-8
dt = datetime(2017, 10, 1, 15, 26, 26, tzinfo=pst)

# Print results
print(dt.isoformat())

# Import tz
from dateutil import tz

# Create a timezone object for Eastern Time
et = tz.gettz('America/New_York')

# Create the timezone object
sm = tz.gettz('Pacific/Apia')

# Pull out the start of the first trip
local = onebike_datetimes[0]['start']

# What time was it in Samoa?
notlocal = local.astimezone(sm)

# Print them out and see the difference
print(local.isoformat())
print(notlocal.isoformat())

# Import datetime, timedelta, tz, timezone
from datetime import datetime, timedelta, timezone
from dateutil import tz

# Start on March 12, 2017, midnight, then add 6 hours
start = datetime(2017, 3, 12, tzinfo = tz.gettz('America/New_York'))
end = start + timedelta(hours=6)
print(start.isoformat() + " to " + end.isoformat())

# How many hours have elapsed?
print((end - start).total_seconds()/(60*60))


# Start on March 12, 2017, midnight, then add 6 hours
start = datetime(2017, 3, 12, tzinfo = tz.gettz('America/New_York'))
end = start + timedelta(hours=6)
print(start.isoformat() + " to " + end.isoformat())

# How many hours have elapsed?
print((end - start).total_seconds()/(60*60))

# What if we move to UTC?
print((end.astimezone(timezone.utc) - start.astimezone(timezone.utc))\
      .total_seconds()/(60*60))

trip_durations = []
for trip in onebike_datetimes:
  # When the start is later than the end, set the fold to be 1
  if trip['start'] > trip['end']:
    trip['end'] = tz.enfold(trip['end'])
  # Convert to UTC
  start = trip['start'].astimezone(timezone.utc)
  end = trip['end'].astimezone(timezone.utc)

  # Subtract the difference
  trip_length_seconds = (end-start).total_seconds()
  trip_durations.append(trip_length_seconds)

# Take the shortest trip duration
print("Shortest trip: " + str(min(trip_durations)))

# Import pandas
import pandas as pd

# Load CSV into the rides variable
rides = pd.read_csv('capital-onebike.csv', 
                    parse_dates = ['Start date','End date'])

# Print the initial (0th) row
print(rides.iloc[0])

# Subtract the start date from the end date
ride_durations = rides['End date'] - rides['Start date']

# Convert the results to seconds
rides['Duration'] = ride_durations.dt.total_seconds()

print(rides['Duration'].head())

# Create joyrides
joyrides = (rides['Start station'] == rides['End station'])

# Total number of joyrides
print("{} rides were joyrides".format(joyrides.sum()))

# Median of all rides
print("The median duration overall was {:.2f} seconds"\
      .format(rides['Duration'].median()))

# Median of joyrides
print("The median duration for joyrides was {:.2f} seconds"\
      .format(rides[rides['Start station'] == rides['End station']]['Duration'].median()))

# Import matplotlib
import matplotlib.pyplot as plt

# Resample rides to daily, take the size, plot the results
rides.resample('D', on = 'Start date')\
  .size()\
  .plot(ylim = [0, 15])

# Show the results
plt.show()

# Import matplotlib
import matplotlib.pyplot as plt

# Resample rides to monthly, take the size, plot the results
rides.resample('M', on = 'Start date')\
  .size()\
  .plot(ylim = [0, 150])

# Show the results
plt.show()

# Resample rides to be monthly on the basis of Start date
monthly_rides = rides.resample('M', on = 'Start date')['Member type']

# Take the ratio of the .value_counts() over the total number of rides
print(monthly_rides.value_counts() / monthly_rides.size())

# Group rides by member type, and resample to the month
grouped = rides.groupby('Member type')\
  .resample('M', on = 'Start date')

# Print the median duration for each group
print(grouped['Duration'].median())

# Localize the Start date column to America/New_York
rides['Start date'] = rides['Start date'].dt.tz_localize('America/New_York', ambiguous='NaT')

# Print first value
print(rides['Start date'].iloc[0])

# Print first value
print(rides['Start date'].iloc[0])

# Convert the Start date column to Europe/London
rides['Start date'] = rides['Start date'].dt.tz_convert('Europe/London')

# Print the new value
print(rides['Start date'].iloc[0])

# Add a column for the weekday of the start of the ride
rides['Ride start weekday'] = rides['Start date'].dt.day_name()

# Print the median trip time per weekday
print(rides.groupby('Ride start weekday')['Duration'].median())

# Shift the index of the end date up one; now subract it from the start date
rides['Time since'] = rides['Start date'] - (rides['End date'].shift(1))

# Move from a timedelta to a number of seconds, which is easier to work with
rides['Time since'] = rides['Time since'].dt.total_seconds()

# Resample to the month
monthly = rides.resample('M', on = 'Start date')

# Print the average hours between rides each month
print(monthly['Time since'].mean()/(60*60))