Add codespell, ruff and fixes

.pre-commit-config.yaml

@@ -1,9 +1,39 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
 repos:
--   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
-    hooks:
-    -   id: check-yaml
-        args: [--unsafe]
-    -   id: end-of-file-fixer
-    -   id: trailing-whitespace
-        args: [--markdown-linebreak-ext=md]
+    - repo: https://github.com/pre-commit/pre-commit-hooks
+      rev: v4.5.0
+      hooks:
+          - id: trailing-whitespace
+          - id: end-of-file-fixer
+          - id: check-yaml
+          - id: check-added-large-files
+          - id: check-ast
+          - id: check-json
+          - id: detect-aws-credentials
+            args: [--allow-missing-credentials]
+          - id: detect-private-key
+    - repo: https://github.com/igorshubovych/markdownlint-cli
+      rev: v0.39.0
+      hooks:
+          - id: markdownlint
+            name: Markdownlint
+            files: \.(md|mdown|markdown)$
+            args: [
+                    "--disable=MD013", # line-length
+                    "--disable=MD033", # no-inline-html
+                ]
+    - repo: https://github.com/codespell-project/codespell
+      rev: v2.2.6
+      hooks:
+          - id: codespell
+            name: codespell
+            description: Checks for common misspellings in text files
+    - repo: https://github.com/astral-sh/ruff-pre-commit
+      rev: v0.2.1
+      hooks:
+          - id: ruff
+            types_or: [python, pyi, jupyter]
+            args: [--fix]
+          - id: ruff-format
+            types_or: [python, pyi, jupyter]

Tutorials/EXAMPLE Finding_links_between_pairs.ipynb

@@ -15,8 +15,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os, sys, time\n",
-    "import rasterio\n",
+    "import os\n",
+    "import sys\n",
     "\n",
     "import networkx as nx\n",
     "import geopandas as gpd\n",
@@ -45,8 +45,12 @@
     "# Define input data\n",
     "pth = \"./\"\n",
     "# Read in cleaned pickle from earlier analysis and convert to time\n",
-    "G = nx.read_gpickle(os.path.join(pth, 'tutorial_outputs', r'iceland_network_clean.pickle'))\n",
-    "G_time = gn.convert_network_to_time(G, distance_tag = 'length', road_col = 'infra_type', factor = 1000)\n",
+    "G = nx.read_gpickle(\n",
+    "    os.path.join(pth, \"tutorial_outputs\", r\"iceland_network_clean.pickle\")\n",
+    ")\n",
+    "G_time = gn.convert_network_to_time(\n",
+    "    G, distance_tag=\"length\", road_col=\"infra_type\", factor=1000\n",
+    ")\n",
     "# Define origins and destinations files\n",
     "rek_grid_file = os.path.join(pth, \"tutorial_data\", \"rek_grid.shp\")\n",
     "rek_pop_grid_file = rek_grid_file.replace(\".shp\", \"_pop.shp\")\n",
@@ -64,10 +68,22 @@
    "outputs": [],
    "source": [
     "# calculate the origins and destinations by snapping to the road network\n",
-    "origins_df = gn.pandana_snap_c(G_time, rek_grid, source_crs='epsg:4326', target_crs='epsg:4326',add_dist_to_node_col = True)\n",
-    "origins = list(set(origins_df['NN']))\n",
-    "destinations_df = gn.pandana_snap_c(G_time, in_churches, source_crs='epsg:4326', target_crs='epsg:4326',add_dist_to_node_col = True)\n",
-    "destinations = list(set(destinations_df['NN']))"
+    "origins_df = gn.pandana_snap_c(\n",
+    "    G_time,\n",
+    "    rek_grid,\n",
+    "    source_crs=\"epsg:4326\",\n",
+    "    target_crs=\"epsg:4326\",\n",
+    "    add_dist_to_node_col=True,\n",
+    ")\n",
+    "origins = list(set(origins_df[\"NN\"]))\n",
+    "destinations_df = gn.pandana_snap_c(\n",
+    "    G_time,\n",
+    "    in_churches,\n",
+    "    source_crs=\"epsg:4326\",\n",
+    "    target_crs=\"epsg:4326\",\n",
+    "    add_dist_to_node_col=True,\n",
+    ")\n",
+    "destinations = list(set(destinations_df[\"NN\"]))"
    ]
   },
   {
@@ -161,10 +177,12 @@
     }
    ],
    "source": [
-    "obj_nodes = nx.shortest_path(G_time, source=origins[0], target=destinations[0], weight=\"time\")\n",
+    "obj_nodes = nx.shortest_path(\n",
+    "    G_time, source=origins[0], target=destinations[0], weight=\"time\"\n",
+    ")\n",
     "print(origins[0])\n",
     "print(destinations[0])\n",
-    "obj_nodes # this is a list of the nodes that connected make the shortest path from the origin to the destination"
+    "obj_nodes  # this is a list of the nodes that connected make the shortest path from the origin to the destination"
    ]
   },
   {
@@ -601,14 +619,18 @@
     "oIdx = 0\n",
     "for org in origins:\n",
     "    oIdx = oIdx + 1\n",
-    "    print(f'{oIdx} of {len(origins)}')\n",
+    "    print(f\"{oIdx} of {len(origins)}\")\n",
     "    for dest in destinations:\n",
     "        obj_nodes = nx.shortest_path(G_time, source=org, target=dest, weight=\"time\")\n",
     "        all_edges = []\n",
     "        for idx in range(0, len(obj_nodes) - 1):\n",
     "            start_node = obj_nodes[idx]\n",
     "            end_node = obj_nodes[idx + 1]\n",
-    "            cur_edge = edges_gdf.loc[(edges_gdf['stnode'] == start_node) & (edges_gdf['endnode'] == end_node), 'geometry'].iloc[0]\n",
+    "            cur_edge = edges_gdf.loc[\n",
+    "                (edges_gdf[\"stnode\"] == start_node)\n",
+    "                & (edges_gdf[\"endnode\"] == end_node),\n",
+    "                \"geometry\",\n",
+    "            ].iloc[0]\n",
     "            all_edges.append(cur_edge)\n",
     "            all_connections.append([start_node, end_node, cur_edge])\n",
     "        all_res.append([org, dest, MultiLineString(all_edges)])"
@@ -621,8 +643,8 @@
    "outputs": [],
    "source": [
     "# Write all connections to file\n",
-    "all_results = pd.DataFrame(all_res, columns=['O','D','geometry'])\n",
-    "all_results.to_csv(os.path.join(pth, \"tutorial_data\",\"all_OD_links.csv\"))"
+    "all_results = pd.DataFrame(all_res, columns=[\"O\", \"D\", \"geometry\"])\n",
+    "all_results.to_csv(os.path.join(pth, \"tutorial_data\", \"all_OD_links.csv\"))"
    ]
   },
   {
@@ -632,12 +654,12 @@
    "outputs": [],
    "source": [
     "# Tabulate usage of individual links and write to file\n",
-    "all_conn = pd.DataFrame(all_connections, columns=['start','node','geometry'])\n",
-    "all_connections_count = pd.DataFrame(all_conn.groupby(['start','node']).count())\n",
+    "all_conn = pd.DataFrame(all_connections, columns=[\"start\", \"node\", \"geometry\"])\n",
+    "all_connections_count = pd.DataFrame(all_conn.groupby([\"start\", \"node\"]).count())\n",
     "all_connections_count.reset_index(inplace=True)\n",
-    "all_connections_first = pd.DataFrame(all_conn.groupby(['start','node']).first())\n",
+    "all_connections_first = pd.DataFrame(all_conn.groupby([\"start\", \"node\"]).first())\n",
     "all_connections_first.reset_index(inplace=True)\n",
-    "all_connections_first['count'] = all_connections_count['geometry']"
+    "all_connections_first[\"count\"] = all_connections_count[\"geometry\"]"
    ]
   },
   {
@@ -646,7 +668,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "all_connections_first.to_csv(os.path.join(pth, \"tutorial_data\",\"OD_links_usage.csv\"))"
+    "all_connections_first.to_csv(os.path.join(pth, \"tutorial_data\", \"OD_links_usage.csv\"))"
    ]
   },
   {

Tutorials/EXAMPLE Fixing your road network.ipynb

@@ -13,8 +13,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os, sys\n",
-    "import time\n",
+    "import os\n",
+    "import sys\n",
     "import networkx as nx\n",
     "import osmnx as ox"
    ]
@@ -36,11 +36,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pth = \"./\" # change this path to your working folder\n",
-    "data_pth = os.path.join(pth, 'tutorial_outputs')\n",
+    "pth = \"./\"  # change this path to your working folder\n",
+    "data_pth = os.path.join(pth, \"tutorial_outputs\")\n",
     "\n",
     "# read back your graph from step 1 from you saved pickle\n",
-    "G = nx.read_gpickle(os.path.join(data_pth, 'iceland_network_clean.pickle'))"
+    "G = nx.read_gpickle(os.path.join(data_pth, \"iceland_network_clean.pickle\"))"
    ]
   },
   {
@@ -50,7 +50,10 @@
    "outputs": [],
    "source": [
     "# note the use of sorted to sort by number of edges\n",
-    "list_of_subgraphs = [G.subgraph(c).copy() for c in sorted(nx.strongly_connected_components(G), key=len, reverse=True)]"
+    "list_of_subgraphs = [\n",
+    "    G.subgraph(c).copy()\n",
+    "    for c in sorted(nx.strongly_connected_components(G), key=len, reverse=True)\n",
+    "]"
    ]
   },
   {
@@ -158,8 +161,8 @@
    ],
    "source": [
     "# plotting functions only work if the graphs have a name and a crs attribute\n",
-    "G_largest.graph['crs'] = 'epsg:32646'\n",
-    "G_largest.graph['name'] = 'Iceland'\n",
+    "G_largest.graph[\"crs\"] = \"epsg:32646\"\n",
+    "G_largest.graph[\"name\"] = \"Iceland\"\n",
     "\n",
     "# largest connected subgraph\n",
     "ox.plot_graph(G_largest, fig_width=10, edge_linewidth=1, node_size=7)"
@@ -193,8 +196,8 @@
     }
    ],
    "source": [
-    "G_second_largest.graph['crs'] = 'epsg:32646'\n",
-    "G_second_largest.graph['name'] = 'Iceland'\n",
+    "G_second_largest.graph[\"crs\"] = \"epsg:32646\"\n",
+    "G_second_largest.graph[\"name\"] = \"Iceland\"\n",
     "\n",
     "# second largest connected subgraph\n",
     "ox.plot_graph(G_second_largest, fig_width=10, edge_linewidth=1, node_size=7)"
@@ -216,7 +219,7 @@
    ],
    "source": [
     "edges_largest = gn.edge_gdf_from_graph(G_largest)\n",
-    "edges_largest.to_csv(os.path.join(data_pth, 'edges_largest.csv'))"
+    "edges_largest.to_csv(os.path.join(data_pth, \"edges_largest.csv\"))"
    ]
   },
   {
@@ -226,7 +229,7 @@
    "outputs": [],
    "source": [
     "edges_second = gn.edge_gdf_from_graph(G_second_largest)\n",
-    "edges_second.to_csv(os.path.join(data_pth, 'edges_second.csv'))"
+    "edges_second.to_csv(os.path.join(data_pth, \"edges_second.csv\"))"
    ]
   },
   {

Tutorials/EXAMPLE Gravity Calculations.ipynb

@@ -6,7 +6,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os, sys, time\n",
+    "import os\n",
+    "import sys\n",
     "import rasterio\n",
     "\n",
     "import networkx as nx\n",
@@ -34,8 +35,12 @@
     "# Define input data\n",
     "pth = \"./\"\n",
     "# Read in cleaned pickle from earlier analysis and convert to time\n",
-    "G = nx.read_gpickle(os.path.join(pth, 'tutorial_outputs', r'iceland_network_clean.pickle'))\n",
-    "G_time = gn.convert_network_to_time(G, distance_tag = 'length', road_col = 'infra_type', factor = 1000)\n",
+    "G = nx.read_gpickle(\n",
+    "    os.path.join(pth, \"tutorial_outputs\", r\"iceland_network_clean.pickle\")\n",
+    ")\n",
+    "G_time = gn.convert_network_to_time(\n",
+    "    G, distance_tag=\"length\", road_col=\"infra_type\", factor=1000\n",
+    ")\n",
     "# Define origins and destinations\n",
     "rek_grid_file = os.path.join(pth, \"tutorial_data\", \"rek_grid.shp\")\n",
     "rek_pop_grid_file = rek_grid_file.replace(\".shp\", \"_pop.shp\")\n",
@@ -67,14 +72,14 @@
     "if not os.path.exists(rek_pop_grid_file):\n",
     "    population_data = \"R:\\GLOBAL\\POP&DEMO\\LandScan_2012\\lspop2012.tif\"\n",
     "\n",
-    "    in_grid = gpd.read_file(rek_grid_file)    \n",
+    "    in_grid = gpd.read_file(rek_grid_file)\n",
     "    in_pop = rasterio.open(population_data)\n",
     "    in_grid = in_grid.to_crs(in_pop.crs)\n",
     "\n",
-    "    geoms = ([x.x, x.y] for x in in_grid['geometry'])\n",
+    "    geoms = ([x.x, x.y] for x in in_grid[\"geometry\"])\n",
     "    vals = in_pop.sample(geoms)\n",
-    "    in_grid['Pop'] = [x[0]+1 for x in vals]\n",
-    "    \n",
+    "    in_grid[\"Pop\"] = [x[0] + 1 for x in vals]\n",
+    "\n",
     "    in_grid.to_file(rek_pop_grid_file)"
    ]
   },
@@ -93,7 +98,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Read in the input \n",
+    "# Read in the input\n",
     "rek_grid = gpd.read_file(rek_pop_grid_file)\n",
     "in_churches = gpd.read_file(churches_file)\n",
     "in_churches = in_churches.to_crs(rek_grid.crs)"
@@ -106,10 +111,22 @@
    "outputs": [],
    "source": [
     "# calculate the origins and destinations by snapping to the road network\n",
-    "origins_df = gn.pandana_snap_c(G_time, rek_grid, source_crs='epsg:4326', target_crs='epsg:4326',add_dist_to_node_col = True)\n",
-    "origins = list(set(origins_df['NN']))\n",
-    "destinations_df = gn.pandana_snap_c(G_time, in_churches, source_crs='epsg:4326', target_crs='epsg:4326',add_dist_to_node_col = True)\n",
-    "destinations = list(set(destinations_df['NN']))"
+    "origins_df = gn.pandana_snap_c(\n",
+    "    G_time,\n",
+    "    rek_grid,\n",
+    "    source_crs=\"epsg:4326\",\n",
+    "    target_crs=\"epsg:4326\",\n",
+    "    add_dist_to_node_col=True,\n",
+    ")\n",
+    "origins = list(set(origins_df[\"NN\"]))\n",
+    "destinations_df = gn.pandana_snap_c(\n",
+    "    G_time,\n",
+    "    in_churches,\n",
+    "    source_crs=\"epsg:4326\",\n",
+    "    target_crs=\"epsg:4326\",\n",
+    "    add_dist_to_node_col=True,\n",
+    ")\n",
+    "destinations = list(set(destinations_df[\"NN\"]))"
    ]
   },
   {
@@ -118,7 +135,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "OD = gn.calculate_OD(G_time, origins, destinations, fail_value = 9999999)"
+    "OD = gn.calculate_OD(G_time, origins, destinations, fail_value=9999999)"
    ]
   },
   {
@@ -129,9 +146,12 @@
    "source": [
     "# The calculate_od_raw contains functions for performing OD and gravity calculations\n",
     "import GOSTnets.calculate_od_raw as calcOD\n",
+    "\n",
     "# For this calculation the origins are all weighted equally with a value of 1\n",
-    "gravity = calcOD.calculate_gravity(OD, oWeight=[1] * OD.shape[0], dWeight = destinations_df['Pop'])\n",
-    "gravity['NN'] = origins"
+    "gravity = calcOD.calculate_gravity(\n",
+    "    OD, oWeight=[1] * OD.shape[0], dWeight=destinations_df[\"Pop\"]\n",
+    ")\n",
+    "gravity[\"NN\"] = origins"
    ]
   },
   {
@@ -152,10 +172,12 @@
    "outputs": [],
    "source": [
     "# Now let's introduce the population numbers into the origins\n",
-    "origins = origins_df['NN']\n",
-    "destinations = destinations_df['NN']\n",
-    "OD = gn.calculate_OD(G_time, origins, destinations, fail_value = 9999999)\n",
-    "gravity = calcOD.calculate_gravity(OD, oWeight=origins_df['Pop'], dWeight = destinations_df['Pop'])"
+    "origins = origins_df[\"NN\"]\n",
+    "destinations = destinations_df[\"NN\"]\n",
+    "OD = gn.calculate_OD(G_time, origins, destinations, fail_value=9999999)\n",
+    "gravity = calcOD.calculate_gravity(\n",
+    "    OD, oWeight=origins_df[\"Pop\"], dWeight=destinations_df[\"Pop\"]\n",
+    ")"
    ]
   },
   {