#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sun Mar 25 23:31:08 2018

@author: megan
"""

import pandas as pd
import scipy.stats as st     # statistical library

# Read in one day of the 2016 Green Taxi Trip Dataset
taxi = pd.read_csv("2016_Green_Taxi_Trip_Data.csv")

# Compute the mean number of passengers per trip.  We are assuming the dataset is the sample.
sample_mean = taxi['Passenger_count'].mean()
# Compute standard deviation of the number of passengers per trip
sample_std_dev = taxi['Passenger_count'].std()

# Count the number of rows in the dataframe.
num_data = len(taxi['Passenger_count'])

# Compute the confidence interval for the mean number of passengers per trip and store it in the variable ci:
# The first option/parameter (0.95) is the confidence level.  So in this example, it is 95%.
# The second option/parameter is the number of degrees of freedom, which is the # of data points - 1
# The third option/parameter is the sample mean.  
# The fourth option/parameter is the sample standard deviation.
ci = st.t.interval(0.95,num_data - 1,loc = sample_mean, scale = sample_std_dev)

# Print out the sample mean and its 95% confidence interval.
print("Mean passengers:",sample_mean)
print("Confidence interval:", ci)