API tools faq
paste
Advertisement
PythonPasteNow

Pasted Python Code

PythonPasteNow
Dec 10th, 2019
133
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 12.91 KB | None | 0 0
raw download clone embed print report
  1. import time
  2. import pandas as pd
  3. import numpy as np
  4.  
  5. CITY_DATA = { 'chicago': 'chicago.csv',
  6.               'new york city': 'new_york_city.csv',
  7.               'washington': 'washington.csv' }
  8.  
  9. def get_filters():
  10.     """
  11.    Asks user to specify a city to analyze.
  12.  
  13.    Returns:
  14.        (str) city 'Birth Year' in df1 - name of the city to analyze
  15.        (str) month - name of the month to filter by, or "all" to apply no month filter
  16.        (str) day - name of the day of week to filter by, or "all" to apply no day filter
  17.    """
  18.     print('\nHello! Let\'s explore some US bikeshare data!')
  19.     # TO DO: get user input for city (chicago, new york city, washington). HINT: Use a while loop to handle invalid inputs
  20.        
  21.     city = input("To view BikeShare information please choose one of the following cities: Chicago, New York City, or Washington  ").lower()
  22.     while city not in ('chicago', 'new york city', 'washington'):
  23.         print("\nPlease choose Chicago, New York City, or Washington")
  24.         city = input("To view BikeShare information please choose one of the following cities: Chicago, New York City, or Washington  ").lower()
  25.     print("\nThank you for choosing {}.".format(city).title())
  26.     #return city
  27.  
  28.     #TO DO: get user input for month (all, jan, feb, mar, apr, may, jun)
  29.     monthchoice = input("\nChoose the month you would like to see from one of the following: All, January, February, March, April, May, or June: ").lower()
  30.     while monthchoice not in ('all', 'january', 'february', 'march', 'april', 'may', 'june'):
  31.         print("\nPlease choose All, January, February, March, April, May, or June")
  32.         monthchoice = input("\nChoose the month you would like to see from one of the following: All, January, February, March, April, May, or June: ").lower()
  33.     print("\nThank you for choosing {}.".format(monthchoice).title())
  34.    
  35.     #TO DO: get user input for day of week (all, mon, tue, wed, thr, fri, sat, sun)
  36.     daychoice = input("\nChoose the day you would like to see from one of the following: All, Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, Sunday: ").lower()
  37.     while daychoice not in ('all', 'monday', 'tuesday', 'wednesday', 'thrusday', 'friday', 'saturday', 'sunday'):
  38.         print("\nPlease choose All, Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, or Sunday")
  39.         daychoice = input("\nChoose the day you would like to see from one of the following: All, Monday, Tuesday, Wednesday, Thursday, Friday, Saturday, Sunday: ").lower()
  40.     print("\nThank you for choosing {}.".format(daychoice).title())
  41.    
  42.    
  43.     print('-'*40)
  44.     return city, monthchoice, daychoice
  45.  
  46.  
  47. def load_data(city, monthchoice, daychoice):
  48.     """
  49.    Loads data for the specified city.
  50.  
  51.    Args:
  52.        (str) city - name of the city to analyze
  53.        (str) monthchoice - name of month to filter by
  54.        (str) daychoice - name of day to filter by
  55.    Returns:
  56.        df1 - Pandas DataFrame containing city data filtered by month and day
  57.    """
  58.     #load data from choosen city
  59.     df1 = pd.read_csv(CITY_DATA[city])
  60.  
  61.     #convert Start Time to dateime
  62.     df1['Start Time'] = pd.to_datetime(df1['Start Time'])
  63.    
  64.     #create monthchoice and daychoice into columns
  65.     df1['monthchoice'] =df1['Start Time'].dt.month
  66.     df1['daychoice'] =df1['Start Time'].dt.weekday_name
  67.    
  68.     #use monthchoice to filter by month, if all don't filter by monthchoice, then create dataframe
  69.     if monthchoice != 'all':
  70.         monthsname = ['january', 'february', 'march', 'april', 'may', 'june']
  71.         monthchoice = monthsname.index(monthchoice) + 1
  72.         df1 = df1[df1['monthchoice'] == monthchoice]
  73.        
  74.     #use daychoice to filter by day, if 'all' don't filter by daychoice, then create dataframe
  75.     if daychoice != 'all':
  76.         dayofweekname = ['monday', 'tuesday', 'wednesday', 'thursday', 'friday', 'saturday', 'sunday']
  77.         daychoice = dayofweekname.index(daychoice) + 1
  78.         df1 = df1[df1['daychoice'] == daychoice]
  79.    
  80.    
  81.    
  82.    
  83.     return df1
  84.  
  85.  
  86. def time_stats(df1):
  87.     """Displays statistics on the most frequent times of travel."""
  88.  
  89.     print('\nCalculating The Most Frequent Times of Travel...\n')
  90.  
  91.     start_time = time.time()
  92.  
  93.     # TO DO: display the most common month
  94.  
  95. #extract month from date/time
  96.     df1['month'] = pd.DatetimeIndex(df1['Start Time']).month
  97.  
  98. #Calculate most popular month - it will be a number
  99.     monthnum = df1['month'].mode()#.values[0]
  100.  
  101. #convert most popular month number to month name
  102.     monthnum = 1
  103.  
  104.     if monthnum == 1:
  105.          monthname = "January"
  106.     elif monthnum == 2:
  107.         monthname = "February"
  108.     elif monthnum == 3:
  109.         monthname = "March"  
  110.     elif monthnum == 4:
  111.        monthname = "April"
  112.     elif monthnum == 5:
  113.        monthname = "May"
  114.     elif monthnum == 6:
  115.        monthname = "June"
  116.  
  117.  
  118.        
  119.     print("\nThe most popular month is {}.".format(
  120.         monthname))
  121.  
  122.  
  123.  
  124.     # TO DO: display the most common day of the week
  125.  
  126. #extract day of the week from date/time
  127.     df1['dayofweek'] = pd.DatetimeIndex(df1['Start Time']).day
  128.  
  129.      
  130. #Calculate most popular day - it will be a number
  131.     daynum = df1['dayofweek'].mode()#.values[0]
  132.  
  133.  
  134. #convert most popular day number to month name
  135.     daynum = 1
  136.  
  137.     if daynum == 1:
  138.         dayname = "Sunday"
  139.     elif daynum == 2:
  140.         dayname = "Monday"
  141.     elif daynum == 3:
  142.         dayname = "Tuesday"  
  143.     elif daynum == 4:
  144.         dayname = "Wednesday"
  145.     elif daynum == 5:
  146.         dayname = "Thursday"
  147.     elif daynum == 6:
  148.         dayname = "Friday"
  149.     elif daynum == 7:
  150.         dayname = "Saturday"
  151.      
  152. #print(dayname) tested and dayname is correct!
  153.  
  154.     print("\nThe most popular day of the week is {}.".format(
  155.         dayname))
  156.  
  157. #extract day of the week from date/time
  158.     df1['hourofday'] = pd.DatetimeIndex(df1['Start Time']).hour
  159.      
  160. #Calculate most popular day - it will be a number
  161.     hournum = df1['hourofday'].mode()#.values[0]
  162.  
  163.  
  164. #convert most popular day number to month name
  165.     hournum = 1
  166.  
  167.     if hournum == 1:
  168.         hourname = "1am"
  169.     elif hournum == 2:
  170.         hourname = "2am"
  171.     elif hournum == 3:
  172.         hourname = "3am"  
  173.     elif hournum == 4:
  174.         hourname = "4am"
  175.     elif hournum == 5:
  176.         hourname = "5am"
  177.     elif hournum == 6:
  178.         hourname = "6am"
  179.     elif hournum == 7:
  180.         hourname = "7am"
  181.     elif hournum == 8:
  182.         hourname = "8am"
  183.     elif hournum == 9:
  184.         hourname = "9am"
  185.     elif hournum == 10:
  186.         hourname = "10am"  
  187.     elif hournum == 11:
  188.         hourname = "11am"
  189.     elif hournum == 12:
  190.         hourname = "12pm"
  191.     elif hournum == 13:
  192.         hourname = "1pm"
  193.     elif hournum == 14:
  194.         hourname = "2pm"
  195.     elif hournum == 15:
  196.         hourname = "3pm"  
  197.     elif hournum == 16:
  198.         hourname = "4pm"
  199.     elif hournum == 17:
  200.         hourname = "5pm"
  201.     elif hournum == 18:
  202.         hourname = "6pm"
  203.     elif hournum == 19:
  204.         hourname = "7pm"
  205.     elif hournum == 20:
  206.         hourname = "8pm"
  207.     elif hournum == 21:
  208.         hourname = "9pm"
  209.     elif hournum == 22:
  210.         hourname = "10pm"  
  211.     elif hournum == 23:
  212.         hourname = "11pm"
  213.     elif hournum == 24:
  214.         hourname = "12am"
  215.  
  216.  
  217. #print(hourname) tested and hourname is correct!
  218.  
  219.     print("\nThe most popular hour of the day is {}.".format(
  220.         hourname))
  221.  
  222.     print("\nThis took %s seconds." % (time.time() - start_time))
  223.     print('-'*40)
  224.  
  225. def station_stats(df1):
  226.     """Displays statistics on the most popular stations and trip."""
  227.  
  228.     print('\nCalculating The Most Popular Stations and Trip...\n')
  229.     start_time = time.time()
  230.  
  231.     # TO DO: display most commonly used start station
  232.     print('\nThe most popular starting station is {}.'.format(
  233.         str(df1['Start Station'].mode().values[0])))
  234.  
  235.     # TO DO: display most commonly used end station
  236.     print('\nThe most popular ending station is {}.'.format(
  237.         str(df1['End Station'].mode().values[0])))
  238.  
  239.     # TO DO: display most frequent combination of start station and end station trip
  240.     df1['startendstation'] = df1['Start Station']+ " to " +df1['End Station']
  241.     print("\nThe most popular trip from start station to end station is {}.".format(
  242.         str(df1['startendstation'].mode().values[0])))
  243.  
  244.     print("\nThis took %s seconds." % (time.time() - start_time))
  245.     print('-'*40)
  246.  
  247.  
  248. def trip_duration_stats(df1):
  249.     """Displays statistics on the total and average trip duration."""
  250.  
  251.     print('\nCalculating Trip Duration...\n')
  252.     start_time = time.time()
  253.  
  254.     # TO DO: display total travel time
  255.     print("\nThe total travel time is {} years.".format(
  256.         str(df1['Trip Duration'].sum()//31536000)))
  257.  
  258.     # TO DO: display mean travel time
  259.     print("\nThe average travel time is {} minutes.".format(
  260.         str(df1['Trip Duration'].mean().astype(int)//60)))
  261.  
  262.     print("\nThis took %s seconds." % (time.time() - start_time))
  263.     print('-'*40)
  264.  
  265.  
  266. def user_stats(df1):
  267.     """Displays statistics on bikeshare users."""
  268.  
  269.     print('\nCalculating User Stats...\n')
  270.     start_time = time.time()
  271.  
  272.     # TO DO: Display counts of user types
  273. ##Old version that showed two columns of pandas table sub/cust and count
  274.     #print("\nThe number of Subscribers or Customers are:")
  275.     #print(df1['User Type'].value_counts())
  276.  
  277.     if 'User Type' in df1:
  278.         print("\nThe number of Subscribers and Customers are:")
  279.         #print(df1['Gender'].value_counts()) old version that was pandas table
  280.         utype_vals = []
  281.         utype_vals = str(df1['User Type'].value_counts()).split()
  282.         #print(utype_vals)  test of utype_vals
  283.         print("\nSubscriber    {}".format(utype_vals[1]))
  284.         print("Customer       {}".format(utype_vals[3]))
  285.    
  286.     # TO DO: Display counts of gender
  287. #Old version that showed two columns of pandas table gender and count
  288. #    if 'Gender' in df1:
  289. #       print("\nThe number of Male and Female customers are:")
  290. #        print(df1['Gender'].value_counts())
  291.  
  292.     if 'Gender' in df1:
  293.         print("\nThe number of Male and Female customers are:")
  294.         #print(df1['Gender'].value_counts()) old version that was pandas table
  295.         gender_vals = []
  296.         gender_vals = str(df1['Gender'].value_counts()).split()
  297.         #print(gender_vals) test of gender_vals
  298.         print("\nMale     {}".format(gender_vals[1]))
  299.         print("Female    {}".format(gender_vals[3]))
  300.  
  301.        
  302.        
  303.        
  304.     # TO DO: Display earliest, most recent, and most common year of birth
  305.     if 'Birth Year' in df1:
  306.         print("\nThe earliest year of birth is {}.".format(
  307.             str(df1['Birth Year'].min().astype(int))))
  308.  
  309.        
  310.         print("\nThe most recent year of birth is {}.".format(
  311.             str(df1['Birth Year'].max().astype(int))))
  312.  
  313.         by = ("\nThe most common year of birth is {}.".format(
  314.             str(df1['Birth Year'].value_counts().head(1).astype(int))))
  315.         print(by.split(".")[0]+'.')
  316.  
  317.  
  318.     print("\nThis took %s seconds." % (time.time() - start_time))
  319.     print('-'*40)
  320.  
  321. #ef rawdata(df1):
  322.     """
  323.    Returns
  324.        5 lines at a time of raw data
  325.    """
  326.  
  327.                
  328. def showraw(df1):
  329.      
  330.         #version that only allows yes or no
  331.    
  332.     startraw = 0
  333.     moreraw = 5
  334.     #rawdata1 = True
  335.     rawdata_more = True
  336.     while(rawdata_more):
  337.         showraw = input('\nWould you like to see 5 lines of raw data?  Type Yes or No: ')
  338.         if showraw.lower() == 'yes':
  339.                 rawdata_more = True
  340.                # rawdata1 = False
  341.                 print(df1[df1.columns[1:9]].iloc[startraw:moreraw])
  342.                 startraw += 5
  343.                 moreraw += 5
  344.                 continue
  345.         elif showraw.lower() == 'no':
  346.                 rawdata_more = False
  347.                 #rawdata1 = False
  348.                 break
  349.         else:
  350.             print("\nPlease answer Yes or No.")
  351.             rawdata_more = True
  352.    
  353.    
  354.    
  355.        
  356. def main():
  357.     while True:
  358.         city, monthchoice, daychoice = get_filters()
  359.         df1= load_data(city, monthchoice, daychoice)
  360.  
  361.         time_stats(df1)
  362.         station_stats(df1)
  363.         trip_duration_stats(df1)
  364.         user_stats(df1)
  365.         showraw(df1)
  366.        
  367.         dorestart = True
  368.         doquestion = True
  369.         while(doquestion):
  370.             restart = input('\nWould you like to restart? Enter yes or no.\n')
  371.             if restart.lower() == 'yes':
  372.                 dorestart = True
  373.                 doquestion = False
  374.                 continue
  375.             elif restart.lower() == 'no':
  376.                 dorestart = False
  377.                 doquestion = False
  378.                 break
  379.             else:
  380.                 print("Please answer Yes or No.")
  381.                 doquestion = True
  382.          
  383.         #End of Yes No question loop
  384.         if dorestart == False:
  385.             break
  386.     #end of restart for script
  387.    
  388.    
  389. if __name__ == "__main__":
  390.     main()
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!