example notebooks

Notebooks

• 00 - What is PyMove?
  • Enviroment settings
  • Using PyMove
  • What can you do with PyMove?
• 01 - Exploring MoveDataFrame
  • MoveDataFrame
  • Creating a MoveDataFrame
    • From a list
    • From a dict
    • From a DataFrame Pandas
    • From a file
  • What’s in MoveDataFrame?
    • 1. The kind of data he was instantiated
    • 1. View trajectory information
    • 2. View the number of users
    • 3. Transform our data to
      • a. Numpy
      • b. Dicts
      • c. DataFrames
    • 4. And even switch from a Pandas to Dask and back again!
    • 5. You can also write files with
    • 6. Create a virtual grid
    • 7. View the information of the last MoveDataFrame operation: operation name, operation time and memory use
    • 8. Get data bound box
    • 9. Create new columns:
      • a. tid: trajectory id based on Id and datetime
      • b. date: extract date on datetime
      • c. hour: extract hour on datetime
      • d. day: day of the week from datatime.
      • e. period: time of day or period from datatime.
      • f. dist_to_prev, time_to_prev, speed_to_prev: create features of distance, time and speed to an GPS point P (lat, lon).
      • g. dist_to_prev, dist_to_next, dist_prev_to_next : three distance in meters to an GPS point P (lat, lon).
      • h. time_to_prev, time_to_next, time_prev_to_next : three time in seconds to an GPS point P (lat, lon).
      • i. speed_to_prev, speed_to_next, speed_prev_to_next : three speed in meters by seconds to an GPS point P (lat, lon).
      • j. dist_to_prev, time_to_prev, speed_to_prev : distance, time and speed from previous ponint
      • K. situation: column with move and stop points by radius.
    • 9. Get time difference between max and min datetime in trajectory data.
    • And that’s it! See upcoming notebooks to learn more about what PyMove can do!
• 02 - Exploring Preprocessing
  • Load data from file
  • Filtering
  • Segmentation
  • Stay point detection
  • Compression
• 03 - Exploring Visualization
  • 1. Imports
  • 2. Load Data
  • 3. Exploring visualization module
    • a. Generate colors
    • b. Exploring data over time
    • c. Exploring trajectories
• 04 - Exploring Grid
  • Imports
  • Load data
  • Create virtual Grid
  • Create one polygon to point on grid
  • Create or update index grid feature
  • Create all polygons to all point on grid
  • Create all polygons on grid
  • Get point to index grid
  • Save grid to .pkl
  • Read .pkl to grid
  • Show a grid polygons
• 05 - Exploring Utils
  • Imports
  • Conversions
  • Datetime
  • Distances
  • Math
  • Trajectories
  • Log
  • Mem
• 06 - Exploring Integrations
  • 0. Required library installations
  • 1. Imports
  • 2. Load Data
    • Visualization
  • 3. Loading points of interest
    • Visualization
  • 4. Integrating Points of Interest into the DataSet
  • 5. Integrating Points of Interest into the DataSet (Using join_with_pois_optimizer)
  • 6. Integrating Points of Interest into the Category-Based DataSet
  • 7. Integrating events (points of interest with timestamp) to the DataSet
  • 8. Integration with Point of Interest HOME
  • 9. Merge of HOME with DataSet already integrated with POIs
  • 11. Union functions
    • Union of Banks
    • Union of Bus Stations
    • Union of Bars and Restaurants
    • Union of Parks
    • Union of police points
  • 12. Integração entre trajetórias e áreas coletivas
• 07 - Exploring Query
  • 1. Imports
  • 2. Load Data
    • Visualization
  • 2. Range Query
    • Using distance MEDP (Mean Euclidean Distance Predictive)
    • Using Distance MEDT (Mean Euclidean Distance Trajectory)
  • 3. KNN (K-Nearest-Neighbor)
    • Using distance MEDP (Mean Euclidean Distance Predictive)
    • Using Distance MEDT (Mean Euclidean Distance Trajectory)
• 08 - Exploring Semantic
  • 1. Imports
  • 2. Load Data