Python - ejercicio_udacity - hacer un filtrado sobre un documento .cvs

from datetime import datetime

import pandas as pd

import numpy as np

CITY_DATA = { 'chicago': 'chicago.csv',

              'new york city': 'new_york_city.csv',

              'washington': 'washington.csv' }

def get_city():

    """

    Asks user to specify a city, month, and day to analyze.

    Returns:

        (str) city - name of the city to analyze

        (str) month - name of the month to filter by, or "all" to apply no month filter

        (str) day - name of the day of week to filter by, or "all" to apply no day filter

    """

     # TO DO: get user input for city (chicago, new york city, washington). HINT: Use a while loop to handle invalid inputs

    city_csv=''

    select_city=''

    while select_city not in ['Chicago','New York City', 'Washington']:

        select_city = input('Hello! Let\'s explore some US bikeshare data! Choose a city between Chicago, New York City and Washington')

        if select_city.title()=='Chicago':

            city_csv='chicago.csv'

            return city_csv

        elif select_city.title()=='New York City':

            city_csv='new_york_city.csv'

            return city_csv

        elif select_city.title()=='Washington':

            city_csv='washington.csv'

            return city_csv

        else:

            print("You did not enter any suggested city. Please, enter Chicago, New York City or Washington"

                  "\n")

def time_filter():

    time_filt=''

    while time_filt not in ['month', 'wday', 'none']:

        time_filt=input("Would you like to filter by month, day of the week or no filtering at all? Please,type 'month', 'wday' or 'none'")

        if time_filt.lower()=='month':

            return time_filt

        if time_filt.lower()=='wday':

            time_filt

            return time_filt

        if time_filt.lower()=='none':

            return time_filt

        else:

            print("The parameter you entered is not correct. Please, type 'month', 'wday' or 'none'")

# TO DO: get user input for month (all, january, february, ... , june)

def get_month():

    MONTHS_DATA={'January':1,'February':2,'March':3,'April':4,'May':5,'June':6}

    select_month=''

    while select_month not in MONTHS_DATA:

        select_month=input("Please, enter a month from the following: January, February, March, April, May and June")

        if select_month.title() not in MONTHS_DATA:

            print("The month selected is not between the mentioned selection. Please, type January, February, March, April, May or June")

        select_month=MONTHS_DATA[(select_month.title())]#--------->>Do return the index(number of the month) with this?

        return select_month

    # TO DO: get user input for day of week (all, monday, tuesday, ... sunday)

def get_wday():

    WDAY_DATA=['Monday', 'Tuesday','Wednesday','Thursday','Friday','Saturday','Sunday','All']

    select_wday=''

    while select_wday.title() not in WDAY_DATA:

         select_wday=input("Please, select a weekday ('Monday', 'Tuesday','Wednesday','Thursday','Friday','Saturday','Sunday') or type 'All' to choose all of"     "them")

    if select_wday.title() not in WDAY_DATA:

        print ("The selected day of the week is not correct. Please tpye 'Monday', 'Tuesday','Wednesday','Thursday','Friday','Saturday','Sunday' or type 'All' to choose all of them")

    elif select_wday.title()=="Monday" or select_wday.title()=="Tuesday" or select_wday.title()=="Wednesday" or select_wday.title()=="Thursday" or           select_wday.title()=="Friday" or select_wday.title()=="Saturday" or select_wday.title()=="Sunday":

        return select_wday

    else:

        select_wday.title=WDAY_DATA[0:] #for "All" input

        return select_wday.title()

def load_data(city_csv,time_filt,select_month, select_wday):

    """

    Loads data for the specified city and filters by month and day if applicable.

    Args:

        (str) city - name of the city to analyze

        (str) month - name of the month to filter by, or "all" to apply no month filter

        (str) day - name of the day of week to filter by, or "all" to apply no day filter

    Returns:

        df - Pandas DataFrame containing city data filtered by month and day

    """

    df=pd.read_csv(city_csv)

    return df

def most_common_month(df):

    """Displays statistics on the most frequent times of travel."""

    print('\nCalculating The Most Frequent Times of Travel...\n')

    df['Start Time']=pd.datetime['Start Time'] #-------->>> Is it correct inside this function??

    df['End Time']=pd.datetime['End Time']#---->>>>Is it correct inside this function??

    # TO DO: display the most common month

    months=['January','February','March','April','May','June']

    index_month=int(df['Start Time'].months.dt.mode())

    most_common_month=months[index_month-1]

    print("The most common month is {}".format(most_common_month))

def most_common_wday(df):

    df['Start Time'] = pd.datetime(df['Start Time'])# I guess it is not required anymore, as it was defined in the function  "most_common_month(df)"

    # TO DO: display the most common day of week

    days=['Monday','Tuesday','Wednesday','Thursday','Friday','Saturday','Sunday']

    index_wday=int(df['Start Time'].dayofweek.dt.mode())

    most_common_wday=days[index_day]

    print("The most common day of the week is {}".format(most_common_wday))

def most_common_start_hour(df):

    df['Start Time'] = pd.datetime(df['Start Time'])# # I guess it is not required anymore, as it was defined in the function  "most_common_month(df)"

    # TO DO: display the most common start hour

    most_common_starth=int(df['Start Time'].hour.dt.mode())

    if most_common_starth==0:

        apm='am'

    elif most_common_starth>0 and most_common_starth<13:

        apm='am'

    elif most_common_starth>=13 and most_common_starth<=24:

        apm='pm'

    print("The most common start hour is {}{}".format(most_commont_starth,apm))

def station_stats(df):

    """Displays statistics on the most popular stations and trip."""

    print('\nCalculating The Most Popular Stations and Trip...\n')

    # TO DO: display most commonly used start station

    most_commonly_start_st=df['Start Station'].mode()

    print("The most commonly used start station is {}".format(most_commonly_start_st))

    # TO DO: display most commonly used end station

    most_commonly_end_st=df['End Station'].mode()

    print("The most commonly used end station is {}".format(most_commonly_end_st))

    # TO DO: display most frequent combination of start station and end station trip

    df['Trip']=df['Start Station'].str.cat(df['End Station'],sep='to')

    most_common_trip=df['Trip'].mode()

    print("The most common trip is {}".format(most_common_trip))

def trip_duration_stats(df):

    """Displays statistics on the total and average trip duration."""

    print('\nCalculating Trip Duration...\n')

    # TO DO: display total travel time

    trip_duration=df['Trip Duration'].sum()

    print("The total trip duration is {}s".format(trip_duration))

    # TO DO: display mean travel time

    trip_mean_dur=df['Trip Duration'].mean()

    print("The total trip duration is {}s".format(trip_mean_dur))

def user_stats(df,city_csv):

    """Displays statistics on bikeshare users."""

    print('\nCalculating User Stats...\n')

    # TO DO: Display counts of user types

    cust=0

    suscr=0

    while df['User Type']=='Suscriber' or df['User Type']=='Customer':

      if df['User Type']=='Suscriber':

          suscr+=1

      else:

          cust+=1

    print("The amount of suscribers is {}".format(suscr))

    print("The amount of suscribers is {}".format(cust))

    # TO DO: Display counts of gender

    if city_csv=='chicago.csv' or city_csv=='new_york_city.csv':

      female=0

      male=0

      while df['Gender']=='Female' or df['Gender']=='Male' or df['Gender']=='':

              if df['Gender']=='Female':

                  female+=1

              elif df['Gender']=='Male':

                  male+=1

              else:

                  female=female

                  male=male

      print("The amount of males is {}".format(male))

      print("The amount of females is {}".format(female))

    # TO DO: Display earliest, most recent, and most common year of birth

    earliest_birthy=str(int(df['Birth Year']).min())

    most_recent_birthy=str(int(df['Birth Year']).max())

    most_common_birthy=str(int(df['Birth Year']).mode())

    print("The earliest year of birth is {}".format(earliest_birthy))

    print("The most recent year of birth is {}".format(most_recent_birthy))

    print("The most common year of birth is {}".format(most_common_birthy))

def main():# XL- Mirar que es exactamente lo que se hace de aqui hacia abajo

    while True:

        city_csv=get_city()

        time_filt=time_filter()

        select_month=get_month()

        select_wday=get_wday()

        df = load_data(city_csv,time_filt, select_month, select_wday)#XL-Las variables son estas???????

        most_common_month(df)

        most_common_wday(df)

        most_common_start_hour(df)

        station_stats(df)

        trip_duration_stats(df)

        user_stats(df, city_csv)

        restart = input('\nWould you like to restart? Enter yes or no.\n')

        if restart.lower() != 'yes':

            break

if __name__ == "__main__":

	main()