Mengyuz

import pandas

def time_to_hour(time):
    '''
    Given an input variable time that represents time in the format of:
    "00:00:00" (hour:minutes:seconds)
    
    Write a function to extract the hour part from the input variable time
    and return it as an integer. For example:
        1) if hour is 00, your code should return 0

Mengyuz

import pandas

def get_hourly_exits(df):
    '''
    The data in the MTA Subway Turnstile data reports on the cumulative
    number of entries and exits per row.  Assume that you have a dataframe
    called df that contains only the rows for a particular turnstile machine
    (i.e., unique SCP, C/A, and UNIT).  This function should change
    these cumulative exit numbers to a count of exits since the last reading
    (i.e., exits since the last row in the dataframe).

Mengyuz

import pandas

def get_hourly_entries(df):
    '''
    The data in the MTA Subway Turnstile data reports on the cumulative
    number of entries and exits per row.  Assume that you have a dataframe
    called df that contains only the rows for a particular turnstile machine
    (i.e., unique SCP, C/A, and UNIT).  This function should change
    these cumulative entry numbers to a count of entries since the last reading
    (i.e., entries since the last row in the dataframe).

Mengyuz

import pandas
import pandasql

def filter_by_regular(filename):
    '''
    This function should read the csv file located at filename into a pandas dataframe,
    and filter the dataframe to only rows where the 'DESCn' column has the value 'REGULAR'.
    
    For example, if the pandas dataframe is as follows:
    ,C/A,UNIT,SCP,DATEn,TIMEn,DESCn,ENTRIESn,EXITSn

Mengyuz

def create_master_turnstile_file(filenames, output_file):
    '''
    Write a function that takes the files in the list filenames, which all have the 
    columns 'C/A, UNIT, SCP, DATEn, TIMEn, DESCn, ENTRIESn, EXITSn', and consolidates
    them into one file located at output_file.  There should be ONE row with the column
    headers, located at the top of the file. The input files do not have column header
    rows of their own.
    
    For example, if file_1 has:
    'C/A, UNIT, SCP, DATEn, TIMEn, DESCn, ENTRIESn, EXITSn'

Mengyuz

import csv

def fix_turnstile_data(filenames):
    '''
    Filenames is a list of MTA Subway turnstile text files. A link to an example
    MTA Subway turnstile text file can be seen at the URL below:
    http://web.mta.info/developers/data/nyct/turnstile/turnstile_110507.txt
    
    As you can see, there are numerous data points included in each row of the
    a MTA Subway turnstile text file. 

Mengyuz

import pandas
import pandasql

def avg_min_temperature(filename):
    '''
    This function should run a SQL query on a dataframe of
    weather data. More specifically you want to find the average
    minimum temperature (mintempi column of the weather dataframe) on 
    rainy days where the minimum temperature is greater than 55 degrees.
    

Mengyuz

import pandas
import pandasql

def avg_weekend_temperature(filename):
    '''
    This function should run a SQL query on a dataframe of
    weather data.  The SQL query should return one column and
    one row - the average meantempi on days that are a Saturday
    or Sunday (i.e., the the average mean temperature on weekends).
    The dataframe will be titled 'weather_data' and you can access

Mengyuz

import pandas
import pandasql


def max_temp_aggregate_by_fog(filename):
    '''
    This function should run a SQL query on a dataframe of
    weather data.  The SQL query should return two columns and
    two rows - whether it was foggy or not (0 or 1) and the max
    maxtempi for that fog value (i.e., the maximum max temperature

Mengyuz

import pandas
import pandasql


def num_rainy_days(filename):
    '''
    This function should run a SQL query on a dataframe of
    weather data.  The SQL query should return one column and
    one row - a count of the number of days in the dataframe where
    the rain column is equal to 1 (i.e., the number of days it