Fix data imports in examples

examples/benchmarking_of_stop_detection_algorithms.ipynb

@@ -50,7 +50,7 @@
     "city = gpd.read_parquet(data_dir / 'garden-city-buildings-mercator.parquet')\n",
     "outer_box = box(*city.total_bounds).buffer(15, join_style='mitre')\n",
     "\n",
-    "filepath_root = 'gc_data_long/'\n",
+    "filepath_root = data_dir / \"gc_data_long\"\n",
     "tc = {\n",
     "    \"user_id\": \"gc_identifier\",\n",
     "    \"timestamp\": \"unix_ts\",\n",

examples/benchmarking_of_stop_detection_algorithms.py

@@ -46,7 +46,7 @@
 city = gpd.read_parquet(data_dir / 'garden-city-buildings-mercator.parquet')
 outer_box = box(*city.total_bounds).buffer(15, join_style='mitre')
 
-filepath_root = 'gc_data_long/'
+filepath_root = data_dir / "gc_data_long"
 tc = {
     "user_id": "gc_identifier",
     "timestamp": "unix_ts",

examples/dbstop_demo.ipynb

@@ -47,7 +47,7 @@
     "city = gpd.read_parquet(data_dir / 'garden-city-buildings-mercator.parquet')\n",
     "outer_box = box(*city.total_bounds)\n",
     "\n",
-    "filepath_root = 'gc_data_long/'\n",
+    "filepath_root = data_dir / \"gc_data_long\"\n",
     "tc = {\"user_id\": \"gc_identifier\", \"x\": \"dev_x\", \"y\": \"dev_y\", \"timestamp\": \"unix_ts\"}\n",
     "\n",
     "# Density based stop detection (Temporal DBSCAN)\n",

examples/generate_synthetic_trajectories.ipynb

@@ -2,243 +2,77 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "10e2517a",
    "metadata": {},
-   "source": [
-    "# Synthetic Trajectory Generation with Nomad\n",
-    "\n",
-    "This notebook demonstrates how to generate realistic synthetic human mobility trajectories."
-   ]
+   "source": "# Synthetic Trajectory Generation with Nomad\n\nThis notebook demonstrates how to generate realistic synthetic human mobility trajectories."
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "58d68e64",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "import time\n",
-    "from pathlib import Path\n",
-    "from joblib import Parallel, delayed\n",
-    "\n",
-    "from nomad.city_gen import City\n",
-    "from nomad.traj_gen import Agent, Population\n",
-    "from nomad.stop_detection.viz import plot_pings, plot_time_barcode"
-   ]
+   "source": "import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport time\nfrom pathlib import Path\nfrom joblib import Parallel, delayed\n\nimport nomad.data as data_folder\nfrom nomad.city_gen import City\nfrom nomad.traj_gen import Agent, Population\nfrom nomad.stop_detection.viz import plot_pings, plot_time_barcode"
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9860e901",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "city = City.from_geopackage('garden-city.gpkg')\n",
-    "city._build_hub_network(hub_size=16)\n",
-    "city.compute_gravity(exponent=2.0)\n",
-    "city.compute_shortest_paths(callable_only=True)\n",
-    "\n",
-    "print(f\"City: {city.name}\")\n",
-    "print(f\"Dimensions: {city.dimensions}\")\n",
-    "print(f\"Buildings: {len(city.buildings_gdf)}\")"
-   ]
+   "source": "data_dir = Path(data_folder.__file__).parent\ncity = City.from_geopackage(data_dir / \"garden-city.gpkg\")\ncity._build_hub_network(hub_size=16)\ncity.compute_gravity(exponent=2.0)\ncity.compute_shortest_paths(callable_only=True)\n\nprint(f\"City: {city.name}\")\nprint(f\"Dimensions: {city.dimensions}\")\nprint(f\"Buildings: {len(city.buildings_gdf)}\")"
   },
   {
    "cell_type": "markdown",
-   "id": "9ff8ddec",
    "metadata": {},
-   "source": [
-    "## Part 1: Effect of Sampling Parameters on Sparsity\n",
-    "\n",
-    "Generate 3 agents with 2-day trajectories, varying beta_duration and beta_start \n",
-    "to show their effect on sparsity (q = observed points / ground truth points)."
-   ]
+   "source": "## Part 1: Effect of Sampling Parameters on Sparsity\n\nGenerate 3 agents with 2-day trajectories, varying beta_duration and beta_start \nto show their effect on sparsity (q = observed points / ground truth points)."
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b6336cc1",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "population = Population(city)\n",
-    "population.generate_agents(N=3, seed=42, name_count=2)\n",
-    "\n",
-    "# Vary beta_duration and beta_start to target different sparsity levels\n",
-    "sampling_params = [\n",
-    "    {'beta_ping': 5, 'beta_start': 100, 'beta_durations': 60},   \n",
-    "    {'beta_ping': 5, 'beta_start': 250, 'beta_durations': 150},  \n",
-    "    {'beta_ping': 5, 'beta_start': 400, 'beta_durations': 240}   \n",
-    "]\n",
-    "\n",
-    "# Generate 2-day trajectories for quick visualization\n",
-    "for i, (agent_id, agent) in enumerate(population.roster.items()):\n",
-    "    agent.generate_trajectory(\n",
-    "        datetime=pd.Timestamp(\"2024-01-01T07:00-04:00\"),\n",
-    "        end_time=pd.Timestamp(\"2024-01-03T07:00-04:00\"),\n",
-    "        seed=i\n",
-    "    )\n",
-    "\n",
-    "    agent.sample_trajectory(\n",
-    "        **sampling_params[i],\n",
-    "        replace_sparse_traj=True,\n",
-    "        seed=i\n",
-    "    )\n",
-    "    \n",
-    "    q = len(agent.sparse_traj) / len(agent.trajectory)\n",
-    "    print(f\"Agent {i}: q={q:.3f}, beta_start={sampling_params[i]['beta_start']}, \"\n",
-    "          f\"beta_dur={sampling_params[i]['beta_durations']}\")"
-   ]
+   "source": "population = Population(city)\npopulation.generate_agents(N=3, seed=42, name_count=2)\n\n# Vary beta_duration and beta_start to target different sparsity levels\nsampling_params = [\n    {'beta_ping': 5, 'beta_start': 100, 'beta_durations': 60},   \n    {'beta_ping': 5, 'beta_start': 250, 'beta_durations': 150},  \n    {'beta_ping': 5, 'beta_start': 400, 'beta_durations': 240}   \n]\n\n# Generate 2-day trajectories for quick visualization\nfor i, (agent_id, agent) in enumerate(population.roster.items()):\n    agent.generate_trajectory(\n        datetime=pd.Timestamp(\"2024-01-01T07:00-04:00\"),\n        end_time=pd.Timestamp(\"2024-01-03T07:00-04:00\"),\n        seed=i\n    )\n\n    agent.sample_trajectory(\n        **sampling_params[i],\n        replace_sparse_traj=True,\n        seed=i\n    )\n    \n    q = len(agent.sparse_traj) / len(agent.trajectory)\n    print(f\"Agent {i}: q={q:.3f}, beta_start={sampling_params[i]['beta_start']}, \"\n          f\"beta_dur={sampling_params[i]['beta_durations']}\")"
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "0e4b20fa",
-   "metadata": {
-    "lines_to_next_cell": 1
-   },
+   "metadata": {},
    "outputs": [],
-   "source": [
-    "fig, axes = plt.subplots(2, 3, figsize=(15, 10), \n",
-    "                         gridspec_kw={'height_ratios': [10, 1]})\n",
-    "\n",
-    "for i, (agent_id, agent) in enumerate(population.roster.items()):\n",
-    "    ax_map = axes[0, i]\n",
-    "    ax_barcode = axes[1, i]\n",
-    "    \n",
-    "    city.plot_city(ax=ax_map, doors=False, address=False)\n",
-    "    \n",
-    "    traj = agent.sparse_traj\n",
-    "    plot_pings(traj, ax=ax_map, s=15, point_color='red', \n",
-    "               x='x', y='y', timestamp='timestamp')\n",
-    "    \n",
-    "    plot_time_barcode(traj['timestamp'], ax=ax_barcode, set_xlim=True)\n",
-    "    \n",
-    "    q = len(traj) / len(agent.trajectory)\n",
-    "    ax_map.set_title(f\"Agent {i}: {len(traj)} obs (q={q:.2f})\\n\"\n",
-    "                     f\"beta_start={sampling_params[i]['beta_start']}, \"\n",
-    "                     f\"beta_dur={sampling_params[i]['beta_durations']}\")\n",
-    "    ax_map.set_axis_off()\n",
-    "\n",
-    "plt.tight_layout()\n",
-    "plt.savefig('data/trajectories_visualization.png', dpi=150, bbox_inches='tight')\n",
-    "plt.show()"
-   ]
+   "source": "fig, axes = plt.subplots(2, 3, figsize=(15, 10), \n                         gridspec_kw={'height_ratios': [10, 1]})\n\nfor i, (agent_id, agent) in enumerate(population.roster.items()):\n    ax_map = axes[0, i]\n    ax_barcode = axes[1, i]\n    \n    city.plot_city(ax=ax_map, doors=False, address=False)\n    \n    traj = agent.sparse_traj\n    plot_pings(traj, ax=ax_map, s=15, point_color='red', \n               x='x', y='y', timestamp='timestamp')\n    \n    plot_time_barcode(traj['timestamp'], ax=ax_barcode, set_xlim=True)\n    \n    q = len(traj) / len(agent.trajectory)\n    ax_map.set_title(f\"Agent {i}: {len(traj)} obs (q={q:.2f})\\n\"\n                     f\"beta_start={sampling_params[i]['beta_start']}, \"\n                     f\"beta_dur={sampling_params[i]['beta_durations']}\")\n    ax_map.set_axis_off()\n\nplt.tight_layout()\nplt.savefig('data/trajectories_visualization.png', dpi=150, bbox_inches='tight')\nplt.show()"
   },
   {
    "cell_type": "markdown",
-   "id": "dc7b266a",
    "metadata": {},
-   "source": [
-    "## Part 2: Parallel Generation at Scale\n",
-    "\n",
-    "Generate trajectories for 15 users using parallelization."
-   ]
+   "source": "## Part 2: Parallel Generation at Scale\n\nGenerate trajectories for 15 users using parallelization."
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5238c745",
-   "metadata": {
-    "lines_to_next_cell": 1
-   },
+   "metadata": {},
    "outputs": [],
-   "source": [
-    "def generate_agent_trajectory(args):\n",
-    "    \"\"\"Worker function for parallel generation.\"\"\"\n",
-    "    identifier, home, work, seed = args\n",
-    "    city = City.from_geopackage('garden-city.gpkg')\n",
-    "    city._build_hub_network(hub_size=16)\n",
-    "    city.compute_gravity(exponent=2.0)\n",
-    "    city.compute_shortest_paths(callable_only=True)\n",
-    "    agent = Agent(identifier=identifier, city=city, home=home, workplace=work)\n",
-    "    \n",
-    "    agent.generate_trajectory(\n",
-    "        datetime=pd.Timestamp(\"2024-01-01T07:00-04:00\"),\n",
-    "        end_time=pd.Timestamp(\"2024-01-08T07:00-04:00\"),\n",
-    "        seed=seed\n",
-    "    )\n",
-    "    agent.sample_trajectory(\n",
-    "        beta_ping=5,\n",
-    "        replace_sparse_traj=True,\n",
-    "        seed=seed\n",
-    "    )\n",
-    "    sparse_df = agent.sparse_traj.copy()\n",
-    "    sparse_df['user_id'] = identifier\n",
-    "    sparse_df['home'] = home\n",
-    "    sparse_df['workplace'] = work\n",
-    "    return sparse_df"
-   ]
+   "source": "def generate_agent_trajectory(args):\n    \"\"\"Worker function for parallel generation.\"\"\"\n    identifier, home, work, seed = args\n    data_dir = Path(data_folder.__file__).parent\n    city = City.from_geopackage(data_dir / \"garden-city.gpkg\")\n    city._build_hub_network(hub_size=16)\n    city.compute_gravity(exponent=2.0)\n    city.compute_shortest_paths(callable_only=True)\n    agent = Agent(identifier=identifier, city=city, home=home, workplace=work)\n    \n    agent.generate_trajectory(\n        datetime=pd.Timestamp(\"2024-01-01T07:00-04:00\"),\n        end_time=pd.Timestamp(\"2024-01-08T07:00-04:00\"),\n        seed=seed\n    )\n    agent.sample_trajectory(\n        beta_ping=5,\n        replace_sparse_traj=True,\n        seed=seed\n    )\n    sparse_df = agent.sparse_traj.copy()\n    sparse_df['user_id'] = identifier\n    sparse_df['home'] = home\n    sparse_df['workplace'] = work\n    return sparse_df"
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "aa1b6112",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "n_agents = 15\n",
-    "rng = np.random.default_rng(100)\n",
-    "homes = city.buildings_gdf[city.buildings_gdf['building_type'] == 'home']['id'].to_numpy()\n",
-    "workplaces = city.buildings_gdf[city.buildings_gdf['building_type'] == 'workplace']['id'].to_numpy()\n",
-    "\n",
-    "agent_params = [\n",
-    "    (f'agent_{i:04d}',\n",
-    "     rng.choice(homes),\n",
-    "     rng.choice(workplaces),\n",
-    "     i)\n",
-    "    for i in range(n_agents)\n",
-    "]"
-   ]
+   "source": "n_agents = 15\nrng = np.random.default_rng(100)\nhomes = city.buildings_gdf[city.buildings_gdf['building_type'] == 'home']['id'].to_numpy()\nworkplaces = city.buildings_gdf[city.buildings_gdf['building_type'] == 'workplace']['id'].to_numpy()\n\nagent_params = [\n    (f'agent_{i:04d}',\n     rng.choice(homes),\n     rng.choice(workplaces),\n     i)\n    for i in range(n_agents)\n]"
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a0364bc9",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "print(f\"Generating {n_agents} agents in parallel...\")\n",
-    "start_time = time.time()\n",
-    "\n",
-    "results = Parallel(n_jobs=-1, verbose=10)(\n",
-    "    delayed(generate_agent_trajectory)(params) for params in agent_params\n",
-    ")\n",
-    "\n",
-    "generation_time = time.time() - start_time\n",
-    "print(f\"Generated {n_agents} agents in {generation_time:.2f}s ({generation_time/n_agents:.2f}s per agent)\")"
-   ]
+   "source": "print(f\"Generating {n_agents} agents in parallel...\")\nstart_time = time.time()\n\nresults = Parallel(n_jobs=-1, verbose=10)(\n    delayed(generate_agent_trajectory)(params) for params in agent_params\n)\n\ngeneration_time = time.time() - start_time\nprint(f\"Generated {n_agents} agents in {generation_time:.2f}s ({generation_time/n_agents:.2f}s per agent)\")"
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "e8a48448",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "parallel_population = Population(city)\n",
-    "for df, params in zip(results, agent_params):\n",
-    "    identifier, home, work, seed = params\n",
-    "    agent = Agent(identifier=identifier, city=city, home=home, workplace=work, seed=seed)\n",
-    "    agent.sparse_traj = df.drop(columns=['home', 'workplace'])\n",
-    "    parallel_population.add_agent(agent, verbose=False)\n",
-    "\n",
-    "output_path = 'data/trajectories_15_users'\n",
-    "parallel_population.save_pop(\n",
-    "    sparse_path=str(output_path),\n",
-    "    fmt='parquet'\n",
-    ")\n",
-    "print(f\"Saved sparse trajectories to {output_path}\")"
-   ]
+   "source": "parallel_population = Population(city)\nfor df, params in zip(results, agent_params):\n    identifier, home, work, seed = params\n    agent = Agent(identifier=identifier, city=city, home=home, workplace=work, seed=seed)\n    agent.sparse_traj = df.drop(columns=['home', 'workplace'])\n    parallel_population.add_agent(agent, verbose=False)\n\nparallel_population.reproject_to_mercator(sparse_traj=True)\n\noutput_path = 'data/trajectories_15_users'\nparallel_population.save_pop(\n    sparse_path=str(output_path),\n    fmt='parquet'\n)\nprint(f\"Saved sparse trajectories to {output_path}\")"
   }
  ],
  "metadata": {
-  "jupytext": {
-   "formats": "ipynb,py:percent"
-  },
   "kernelspec": {
    "display_name": "Python 3 (ipykernel)",
    "language": "python",

examples/generate_synthetic_trajectories.py

@@ -26,12 +26,14 @@
 from pathlib import Path
 from joblib import Parallel, delayed
 
+import nomad.data as data_folder
 from nomad.city_gen import City
 from nomad.traj_gen import Agent, Population
 from nomad.stop_detection.viz import plot_pings, plot_time_barcode
 
 # %%
-city = City.from_geopackage('garden-city.gpkg')
+data_dir = Path(data_folder.__file__).parent
+city = City.from_geopackage(data_dir / "garden-city.gpkg")
 city._build_hub_network(hub_size=16)
 city.compute_gravity(exponent=2.0)
 city.compute_shortest_paths(callable_only=True)
@@ -110,7 +112,8 @@
 def generate_agent_trajectory(args):
     """Worker function for parallel generation."""
     identifier, home, work, seed = args
-    city = City.from_geopackage('garden-city.gpkg')
+    data_dir = Path(data_folder.__file__).parent
+    city = City.from_geopackage(data_dir / "garden-city.gpkg")
     city._build_hub_network(hub_size=16)
     city.compute_gravity(exponent=2.0)
     city.compute_shortest_paths(callable_only=True)
@@ -165,6 +168,8 @@ def generate_agent_trajectory(args):
     agent.sparse_traj = df.drop(columns=['home', 'workplace'])
     parallel_population.add_agent(agent, verbose=False)
 
+parallel_population.reproject_to_mercator(sparse_traj=True)
+
 output_path = 'data/trajectories_15_users'
 parallel_population.save_pop(
     sparse_path=str(output_path),

examples/grid_based_demo.ipynb

@@ -48,7 +48,7 @@
     "city = gpd.read_parquet(data_dir / 'garden-city-buildings-mercator.parquet')\n",
     "outer_box = box(*city.total_bounds)\n",
     "\n",
-    "filepath_root = 'gc_data_long/'\n",
+    "filepath_root = data_dir / \"gc_data_long\"\n",
     "tc = {\"user_id\": \"gc_identifier\", \"x\": \"dev_x\", \"y\": \"dev_y\", \"timestamp\": \"unix_ts\"}\n",
     "\n",
     "users = ['admiring_brattain']\n",

examples/grid_based_demo.py

@@ -45,7 +45,7 @@
 city = gpd.read_parquet(data_dir / 'garden-city-buildings-mercator.parquet')
 outer_box = box(*city.total_bounds)
 
-filepath_root = 'gc_data_long/'
+filepath_root = data_dir / "gc_data_long"
 tc = {"user_id": "gc_identifier", "x": "dev_x", "y": "dev_y", "timestamp": "unix_ts"}
 
 users = ['admiring_brattain']

examples/hdbscan_demo.ipynb

@@ -41,7 +41,7 @@
     "city = gpd.read_parquet(data_dir / 'garden-city-buildings-mercator.parquet')\n",
     "outer_box = box(*city.total_bounds)\n",
     "\n",
-    "filepath_root = 'gc_data_long/'\n",
+    "filepath_root = data_dir / \"gc_data_long\"\n",
     "tc = {\"user_id\": \"gc_identifier\", \"x\": \"dev_x\", \"y\": \"dev_y\", \"timestamp\": \"unix_ts\"}\n",
     "\n",
     "users = ['admiring_brattain']\n",

examples/hdbscan_demo.py

@@ -39,7 +39,7 @@
 city = gpd.read_parquet(data_dir / 'garden-city-buildings-mercator.parquet')
 outer_box = box(*city.total_bounds)
 
-filepath_root = 'gc_data_long/'
+filepath_root = data_dir / "gc_data_long"
 tc = {"user_id": "gc_identifier", "x": "dev_x", "y": "dev_y", "timestamp": "unix_ts"}
 
 users = ['admiring_brattain']