spell check

Examples/Scripts/Python/MLAmbiguityResolution/seed_filter_full_chain.py

@@ -63,7 +63,7 @@ def clusterSeed(
     @param[in] event: input DataFrame that contain all track in one event
     @param[in] DBSCAN_eps: minimum radius used by the DBSCAN to cluster track together
     @param[in] DBSCAN_min_samples: minimum number of tracks needed for DBSCAN to create a cluster
-    @return: DataFrame identical to the output with an added collumn with the cluster 
+    @return: DataFrame identical to the output with an added column with the cluster 
     """
     # Perform the DBSCAN clustering and sort the Db by cluster ID
     trackDir = event[["eta", "phi", "vertexZ", "pT"]].to_numpy()
@@ -152,7 +152,7 @@ def renameCluster(clusterarray: np.ndarray) -> np.ndarray:
     plt.clf()
 
 
-# Create historgram filled with the number of seed per cluster
+# Create histogram filled with the number of seed per cluster
 for event in plotData:
     event["nb_seed"] = 0
     event["nb_fake"] = 0
@@ -169,7 +169,7 @@ def renameCluster(clusterarray: np.ndarray) -> np.ndarray:
     plt.ylabel("nb cluster")
     plt.savefig("nb_seed.png")
     plt.clf()
-    # Create historgram filled with the number of fake seed per cluster
+    # Create histogram filled with the number of fake seed per cluster
     event.loc[event["good/duplicate/fake"] == "fake", "nb_fake"] = (
         event.loc[event["good/duplicate/fake"] == "fake"]
         .groupby(["cluster"])["cluster"]
@@ -180,7 +180,7 @@ def renameCluster(clusterarray: np.ndarray) -> np.ndarray:
     plt.ylabel("nb cluster")
     plt.savefig("nb_fake.png")
     plt.clf()
-    # Create historgram filled with the number of duplicate seed per cluster
+    # Create histogram filled with the number of duplicate seed per cluster
     event.loc[event["good/duplicate/fake"] == "duplicate", "nb_duplicate"] = (
         event.loc[event["good/duplicate/fake"] == "duplicate"]
         .groupby(["cluster"])["cluster"]
@@ -191,7 +191,7 @@ def renameCluster(clusterarray: np.ndarray) -> np.ndarray:
     plt.ylabel("nb cluster")
     plt.savefig("nb_duplicate.png")
     plt.clf()
-    # Create historgram filled with the number of good seed per cluster
+    # Create histogram filled with the number of good seed per cluster
     event.loc[event["good/duplicate/fake"] == "good", "nb_good"] = (
         event.loc[event["good/duplicate/fake"] == "good"]
         .groupby(["cluster"])["cluster"]
@@ -202,22 +202,22 @@ def renameCluster(clusterarray: np.ndarray) -> np.ndarray:
     plt.ylabel("nb cluster")
     plt.savefig("nb_good.png")
     plt.clf()
-    # Create historgram filled with the number of truth particle per cluster
+    # Create histogram filled with the number of truth particle per cluster
     event["nb_truth"] = event.groupby(["cluster"])["particleId"].transform("nunique")
     event["nb_truth"].hist(bins=10, range=[0, 10])
     plt.xlabel("nb truth")
     plt.ylabel("nb cluster")
     plt.savefig("nb_truth.png")
     plt.clf()
-    # Create historgram filled with the number of cluser per truth particle
+    # Create histogram filled with the number of cluster per truth particle
     event["nb_cluster"] = event.groupby(event.index)["cluster"].transform("nunique")
     event["nb_cluster"].hist(bins=30, weights=1 / event["nb_seed"], range=[0, 30])
     plt.xlabel("nb cluster")
     plt.ylabel("nb truth")
     plt.savefig("nb_cluster.png")
     plt.clf()
 
-    # Create historgram filled with the number of good cluser with more than one
+    # Create histogram filled with the number of good cluster with more than one
     event["nb_good"].hist(bins=10, weights=(event["nb_seed"] > 1) / event["nb_seed"])
     plt.xlabel("nb good cluster with more than 1 seed")
     plt.ylabel("nb cluster")
@@ -234,7 +234,7 @@ def renameCluster(clusterarray: np.ndarray) -> np.ndarray:
     x = torch.tensor(x_test, dtype=torch.float32)
     output_predict = duplicateClassifier(x).detach().numpy()
 
-    # creat an array of random value between 0 and 1 of the same size as the output
+    # Create an array of random value between 0 and 1 of the same size as the output
     # output_predict = np.random.rand(len(x_test))
 
     clusteredEvent["score"] = output_predict
@@ -244,7 +244,7 @@ def renameCluster(clusterarray: np.ndarray) -> np.ndarray:
     )
     cleanedEvent = clusteredEvent[idx]
 
-    # For each cluster only keep the track with the higest score
+    # For each cluster only keep the track with the highest score
     idx = (
         cleanedEvent.groupby(["cluster"])["score"].transform(max)
         == cleanedEvent["score"]

Examples/Scripts/Python/MLAmbiguityResolution/seed_solver_network.py

@@ -12,7 +12,7 @@ def prepareDataSet(data: pd.DataFrame) -> pd.DataFrame:
     """Format the dataset that have been written from the Csv file"""
     """
     @param[in] data: input DataFrame containing 1 event
-    @return: Formated DataFrame 
+    @return: Formatted DataFrame 
     """
     data = data
     data = data.sort_values("good/duplicate/fake", ascending=False)

Examples/Scripts/Python/MLAmbiguityResolution/train_seed_solver.py

@@ -166,7 +166,7 @@ def scoringBatch(batch: list[pd.DataFrame], Optimiser=0) -> tuple[int, int, floa
     max_match = 1
     # loop over all the batch
     for b_data in batch:
-        # ID of the current particule
+        # ID of the current particle
         pid = b_data[0][0]
         # loss for the current batch
         batch_loss = 0
@@ -184,7 +184,7 @@ def scoringBatch(batch: list[pd.DataFrame], Optimiser=0) -> tuple[int, int, floa
         prediction = duplicateClassifier(input)
         # loop over all the seed in the batch
         for index, pred, truth in zip(b_data[0], prediction, b_data[2]):
-            # If we are changing particle uptade the loss
+            # If we are changing particle update the loss
             if index != pid:
                 # Starting a new particles, compute the loss for the previous one
                 if max_match == 0 or max_match == 2:
@@ -237,7 +237,7 @@ def scoringBatch(batch: list[pd.DataFrame], Optimiser=0) -> tuple[int, int, floa
         # Normalise the loss to the batch size
         batch_loss = batch_loss / len(b_data[0])
         loss += batch_loss
-        # Perform the gradient decend if an optimiser was specified
+        # Perform the gradient descent if an optimiser was specified
         if Optimiser:
             batch_loss.backward()
             Optimiser.step()

Plugins/Mlpack/include/Acts/Plugins/Mlpack/SeedFilterDBScanClustering.hpp

@@ -16,7 +16,7 @@
 
 namespace Acts {
 
-/// Clusterise seed based on their Z position, their direction and their
+/// Clusters seed based on their Z position, their direction and their
 /// momentum using DBScan
 ///
 /// @param input : Input parameters for the clustering (phi, eta, z, Pt/10)
@@ -26,7 +26,7 @@ namespace Acts {
 std::vector<std::vector<int>> dbscanSeedClustering(
     const std::vector<std::vector<double>>& input, float epsilon = 0.07,
     int minPoints = 2) {
-  // DBSCAN algoritm from MLpack used in the seed clustering
+  // DBSCAN algorithm from MLpack used in the seed clustering
   mlpack::DBSCAN dbscan(epsilon, minPoints);
 
   // Compute the space dimension of the input

Plugins/Onnx/include/Acts/Plugins/Onnx/SeedClassifier.hpp

@@ -70,15 +70,15 @@ class SeedClassifier {
   /// @param clusters is a map of clusters, each cluster correspond to a vector of seed ID
   /// @param networkInput input of the network
   /// @return a vector of seedID corresponding the the good seeds
-  std::vector<int> solveAmbuguity(std::vector<std::vector<int>>& clusters,
+  std::vector<int> solveAmbiguity(std::vector<std::vector<int>>& clusters,
                                   Acts::NetworkBatchInput& networkInput) const {
     std::vector<std::vector<float>> outputTensor = inferScores(networkInput);
     std::vector<int> goodSeeds = seedSelection(clusters, outputTensor);
     return goodSeeds;
   }
 
  private:
-  // ONNX environement
+  // ONNX environment
   Ort::Env m_env;
   // ONNX model for the duplicate neural network
   Acts::OnnxRuntimeBase m_duplicateClassifier;