import time as time
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_filters():
    """
    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
    """
    print('Hello! Let\'s explore some US bikeshare data!')
    # get user input for city (chicago, new york city, washington). HINT: Use a while loop to handle invalid inputs
    while True:
        city = input('Please choose a city (Chicago, New York City, Washington):\n').lower()
        if city not in ('chicago', 'new york city', 'washington'):
            print('Wrong input! Please choose a city (Chicago, New York City, Washington):\n')
            continue
        else:
            break

    # get user input for month (all, january, february, ... , june)
    while True:
        month = input('Please choose a month (January, February, March, April, May, June or all:\n').lower()
        if month not in ('january', 'february', 'march', 'april', 'may', 'june', 'all'):
            print('Wrong input! Please choose a month (January, February, March, April, May, June or all:\n')
            continue
        else:
            break

    # get user input for day of week (all, monday, tuesday, ... sunday)
    while True:
        day = input('Please choose a day (Monday, Tuesday, ... Sunday or all:\n').lower()
        if day not in ('monday', 'tuesday', 'wednesday', 'thursday', 'friday', 'saturday', 'sunday', 'all'):
            print('Wrong input! Please choose a day (Monday, Tuesday, ... Sunday or all:\n')
            continue
        else:
            break

    print('-'*40)
    return city, month, day


def load_data(city, month, day):
    """
    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_DATA[city])

    df['Start Time'] = pd.to_datetime(df['Start Time'])
    df['month'] = df['Start Time'].dt.month
    df['day_of_week'] = df['Start Time'].dt.weekday_name
    df['hour'] = df['Start time'].dt.hour

    if months != 'all':
        months = ['january', 'february', 'march', 'april', 'may', 'june']
        month = months.index(month) + 1
        df = df[df['month'] == month]

    if day != 'all':
        df = df[df['day_of_week'] == day.title()]

    return df


def time_stats(df):
    """Displays statistics on the most frequent times of travel."""

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

    # display the most common month
    popular_month = df['month'].mode()[0] - 1
    print('The most popular month is {}.'.format(months[popular_month].title()))

    # display the most common day of week
    popular_day = df['day_of_week'].mode()[0]
    print('The most popular day of week is {}.'.format(popular_day))

    # display the most common start hour
    popular_hour = df['hour'].mode()[0]
    print('The most popular hour is {}.'.format(popular_hour))

    print("\nThis took %s seconds." % (time.time() - start_time))
    print('-'*40)


def station_stats(df):
    """Displays statistics on the most popular stations and trip."""

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

    # display most commonly used start station
    popular_start_station = df['Start Station'].mode()[0]
    print('{} is the most popular start station.'.format(popular_start_station))

    # display most commonly used end station
    popular_end_station = df['End Station'].mode()[0]
    print('{} is the most popular end station.'.format(popular_end_station))

    # display most frequent combination of start station and end station trip
    station_pair = df.groupby(['Start Station', 'End Station']).size().nlargest(1).reset_index(name='count')
    print('The most frequent combination of stations is {} (start) and {} (end).\nThis route was used {} time(s).'.format(station_pair['Start Station'][0], station_pair['End Station'][0], station_pair['count'][0]))

    print("\nThis took %s seconds." % (time.time() - start_time))
    print('-'*40)


def trip_duration_stats(df):
    """Displays statistics on the total and average trip duration."""

    print('\nCalculating Trip Duration...\n')
    start_time = time.time()

    df['End Time'] = pd.to_datetime(df['End Time'])
    df['Trip Duration'] = df['End Time'] - df['Start Time']
    # display total travel time
    total_travel_time = df['Trip Duration'].sum()
    print('Total travel time of all bike rides is {}.'.format(total_travel_time))
    # display mean travel time
    mean_travel_time = df['Trip Duration'].mean()
    print('Mean travel time is {}.'.format(mean_travel_time))

    print("\nThis took %s seconds." % (time.time() - start_time))
    print('-'*40)


def user_stats(df):
    """Displays statistics on bikeshare users."""

    print('\nCalculating User Stats...\n')
    start_time = time.time()

    # Display counts of user types
    user_type_count = df['User Type'].value_counts()
    print('User counts:\n', user_type_count)

    # Display counts of gender
    gender_count = df['Gender'].value_counts()
    print('Gender counts:\n', gender_count)

    # Display earliest, most recent, and most common year of birth
    min_year = df['Birth Year'].min()
    print('The earliest year of birth is {}.'.format(min_year))

    max_year = df['Birth Year'].max()
    print('The most recent year of birth is {}.'.format(max_year))

    common_year = df['Birth Year'].mode()[0]
    print('The most common year of birth is {}.'.format(common_year))

    print("\nThis took %s seconds." % (time.time() - start_time))
    print('-'*40)


def main():
    while True:
        city, month, day = get_filters()
        df = load_data(city, month, day)

        time_stats(df)
        station_stats(df)
        trip_duration_stats(df)
        user_stats(df)

        restart = input('\nWould you like to restart? Enter yes or no.\n')
        if restart.lower() != 'yes':
            break


if __name__ == "__main__":
    main()