Cleanup

.github/workflows/black.yml

@@ -64,4 +64,4 @@ jobs:
 
       - name: Format with black
         run: |
-          poetry run black 'p6' --check
+          poetry run black nfopt --check

README.md

@@ -66,7 +66,7 @@ The optimizer can generate a baseline using uniform path splitting ratios for tr
 ### Data Format
 Before you can start using the tool, ensure the following steps are completed:
 
-1. **Data Formatting:** Make sure your data is formatted according to the examples provided in the `example-data` directory.
+1. **Data Formatting:** Make sure your data is formatted according to the examples provided in the `sample-data` directory.
 2. **Environment Variables:** Set the environment variable for the data directory correctly in the `variables.env` file. You can use the `variables.env-example` file as a reference for the required environment variables and their values. Rename `variables.env-example` to `.env` and update it with the appropriate information.
 
 ### Usage

p6/linear_optimization/netflow.py → nfopt/linear_optimization/netflow.py

@@ -4,13 +4,15 @@
 from collections import deque
 
 from dotenv import load_dotenv
-from p6.utils import log
-from p6.utils import data as dataUtils
-
+from nfopt.utils import log
+from nfopt.utils import data as dataUtils
 
 logger = log.setupCustomLogger(__name__)
 load_dotenv("variables.env")
 
+NETFLOW_FLOW_THRESHOLD = float(os.getenv("NETFLOW_FLOW_THRESHOLD"))
+NETFLOW_PATHS_THRESHOLD = float(os.getenv("NETFLOW_PATHS_THRESHOLD"))
+
 options = {
     "WLSACCESSID": os.getenv("WLSACCESSID"),
     "WLSSECRET": os.getenv("WLSSECRET"),
@@ -19,9 +21,24 @@
 
 
 def optMC(parserArgs, links, flowTraffic, timestamp):
-    with gp.Env(params=options) as env, gp.Model(env=env) as m:
-        m = gp.Model("netflow", env=env)
+    """
+    Runs multi-commodity flow problem optimization on the data using Gurobi. Writes a file with the new paths and their ratios.
+
+    ### Parameters:
+    ----------
+    #### parserArgs: argparse.Namespace
+    The parser arguments.
+
+    #### links: dict
+    The links in the network, indexed by linkName.
 
+    #### flowTraffic: dict
+    The traffic for each source-destination pair.
+
+    #### timestamp: string
+    The timestamp for the current data.
+    """
+    with gp.Env(params=options) as env, gp.Model("netflow", env=env) as m:
         nodes = []
         edges = []
         for link in links:
@@ -37,9 +54,11 @@ def optMC(parserArgs, links, flowTraffic, timestamp):
         sorted_flowTraffic = sorted(
             flowTraffic.items(), key=lambda item: item[1], reverse=True
         )
+
         total_demand = sum(flowTraffic.values())
-        percentage = 0.2  # TODO: Add this as a parameter
+        percentage = NETFLOW_FLOW_THRESHOLD
         demand_threshold = total_demand * percentage
+
         cumulative_demand = 0
         significant_flowTraffic = {}
         for flow, value in sorted_flowTraffic:
@@ -114,7 +133,7 @@ def optMC(parserArgs, links, flowTraffic, timestamp):
         m.optimize()
 
     # Define the threshold percentage (e.g., 10%)
-    threshold_percentage = 0.001
+    threshold_percentage = 1 - NETFLOW_PATHS_THRESHOLD
 
     if m.Status == gp.GRB.OPTIMAL:
         solution = m.getAttr("X", flowVars)

p6/linear_optimization/optimizer.py → nfopt/linear_optimization/optimizer.py

@@ -6,9 +6,9 @@
 from gurobipy import GRB
 from dotenv import load_dotenv
 
-from p6.calc_type_enum import CalcType
-from p6.utils import log
-from p6.utils import data as dataUtils
+from nfopt.calc_type_enum import CalcType
+from nfopt.utils import log
+from nfopt.utils import data as dataUtils
 
 logger = log.setupCustomLogger(__name__)
 
@@ -52,10 +52,7 @@ def runLinearOptimizationModel(
     logger.info("Started running linear optimization model...")
     model = parserArgs.model_type
 
-    with gp.Env(params=options) as env, gp.Model(env=env) as m:
-        # Create optimization model based on the input model
-        m = gp.Model("network_optimization", env=env)
-
+    with gp.Env(params=options) as env, gp.Model("network_optimization", env=env) as m:
         # Decision variables for path ratios for each source-destination pair
         path_ratios = m.addVars(
             [

p6/main.py → nfopt/main.py

@@ -6,11 +6,11 @@
 
 from multiprocessing import set_start_method
 
-from p6.calc_type_enum import CalcType
-from p6.utils import data as dataUtils
-from p6.utils import network as nwUtils
-from p6.utils import log
-from p6.linear_optimization import netflow, optimizer as linOpt
+from nfopt.calc_type_enum import CalcType
+from nfopt.utils import data as dataUtils
+from nfopt.utils import network as nwUtils
+from nfopt.utils import log
+from nfopt.linear_optimization import netflow, optimizer as linOpt
 
 logger = log.setupCustomLogger(__name__)
 
@@ -211,7 +211,7 @@ def main():
             ],
         )
 
-    if results[0] is not None:
+    if results is not None:
         results.sort()
 
         dataUtils.writeDataToFile(

p6/utils/data.py → nfopt/utils/data.py

@@ -3,7 +3,7 @@
 import pandas as pd
 import multiprocessing as mp
 
-from p6.utils import log
+from nfopt.utils import log
 from functools import partial
 from datetime import datetime
 from dotenv import load_dotenv
@@ -134,8 +134,7 @@ def readLinks():
 
         logger.info("Reading links...")
         dataCapacity = pd.read_csv(
-            f"{DATASET_PATH}/{DATASET_LINKS_NAME}.csv.gz",
-            compression="gzip",
+            f"{DATASET_PATH}/{DATASET_LINKS_NAME}.csv",
             names=["linkStart", "linkEnd", "capacity"],
             skiprows=1,
             engine="pyarrow",

p6/utils/network.py → nfopt/utils/network.py

@@ -1,4 +1,4 @@
-from p6.utils import log
+from nfopt.utils import log
 
 logger = log.setupCustomLogger(__name__)