The dataset used here is the New York City Taxi Demand dataset. The raw data is from the NYC Taxi and Limousine Commission. The data included here consists of aggregating the total number of taxi passengers into 30 minute buckets. In this question, we will simply process the data and explore the time series.

• Create two new dataframes df_day and df_hour by aggregating the demand value on daily and hourly level.

• Plot the demand value in two line charts for both df_day and df_hour dataframes.

• Plot the seasonal decomposition components (Trend, Seasonal, Residual) from df_day dataframe, also find out the p value from adfuller test. Do you think the df_day is stationary enough (please explain your reasons in comments and report)?

Answer rating: 100% (QA)

To process and explore the New York City Taxi Demand dataset we will follow the provided steps 1 Aggregating the dataset on a daily and hourly level T... View the full answer