fix: introduce constants.py

Author: wilsonify

src/common/constants.py

@@ -0,0 +1,22 @@
+"""Shared constants used across modules to avoid duplicated string literals.
+
+Placing these constants in a single module reduces duplicated literal occurrences
+and makes it easier to update canonical module paths in one place.
+"""
+
+# Working-with-data module base
+WORKING_DATA_MODULE = 'dsl.c10_working_with_data'
+
+# Common working-data suffixes used multiple times in the codebase
+E1004 = '.e1004_named_tuples'
+E1006 = '.e1006_cleaning'
+E1007 = '.e1007_manipulation'
+E1008 = '.e1008_rescaling'
+E1009 = '.e1009_dimensionality_reduction'
+
+# Fully qualified working-data module constants
+WORKING_E1004 = WORKING_DATA_MODULE + E1004
+WORKING_E1006 = WORKING_DATA_MODULE + E1006
+WORKING_E1007 = WORKING_DATA_MODULE + E1007
+WORKING_E1008 = WORKING_DATA_MODULE + E1008
+WORKING_E1009 = WORKING_DATA_MODULE + E1009

src/data-scratch-amqp/data_scratch_amqp/strategies_library/dynamic_strategy.py

@@ -238,8 +238,8 @@ def main2(path_to_stocks):
     ys1 = [x + random_normal() / 2 for x in xs]
     ys2 = [-x + random_normal() / 2 for x in xs]
 
-    logging.info("Correlation(xs, ys1) = %", correlation(xs, ys1))
-    logging.info("Correlation(xs, ys2) = %", correlation(xs, ys2))
+    logging.info("Correlation(xs, ys1) = %s", correlation(xs, ys1))
+    logging.info("Correlation(xs, ys2) = %s", correlation(xs, ys2))
 
     logging.info("Analyzing stocks...")
     _data = read_stocks_txt(path_to_stocks)

src/data-scratch-library/dsl/c10_working_with_data/e01_working_with_data.py

@@ -56,7 +56,7 @@ def get_all_library_functions():
         MATRICES_MODULE: ['shape', 'get_row', 'get_column', 'make_matrix', 'is_diagonal', 'make_identity_matrix', 'matrix_add', 'matrix_multiply', 'make_random_matrix'],
         CENTRAL_TENDENCY_MODULE: ['mean', 'median', 'quantile', 'mode'],
         DISPERSION_MODULE: ['data_range', 'de_mean', 'variance', 'standard_deviation', 'interquartile_range'],
-        CORRELATION_MODULE: ['covariance', 'correlation', 'correlation_matrix'],
+    CORRELATION_MODULE: ['covariance', 'correlation'],
         UNIFORM_MODULE: ['uniform_pd', 'uniform_cd'],
         NORMAL_MODULE: ['normal_pd', 'normal_cd', 'inverse_normal_cd'],
         BINOM_MODULE: ['bernoulli_trial', 'binomial', 'binom_pd', 'binom_cd', 'binom_pp'],
@@ -70,21 +70,25 @@ def get_all_library_functions():
 
     # Simple helper modules for other grouped functions
     ML_MODULE = 'dsl.c11_machine_learning.machine_learning'
-    WORKING_DATA_MODULE = 'dsl.c10_working_with_data'
-
-    # Common working-data suffixes used multiple times — extract to constants
-    E1004 = '.e1004_named_tuples'
-    E1006 = '.e1006_cleaning'
-    E1007 = '.e1007_manipulation'
-    E1008 = '.e1008_rescaling'
-    E1009 = '.e1009_dimensionality_reduction'
-
-    # Fully qualified working-data module constants to avoid repeated concatenations
-    WORKING_E1004 = WORKING_DATA_MODULE + E1004
-    WORKING_E1006 = WORKING_DATA_MODULE + E1006
-    WORKING_E1007 = WORKING_DATA_MODULE + E1007
-    WORKING_E1008 = WORKING_DATA_MODULE + E1008
-    WORKING_E1009 = WORKING_DATA_MODULE + E1009
+    try:
+        # Prefer shared constants module to reduce duplicated literals across files
+        from common.constants import (
+            WORKING_DATA_MODULE,
+            WORKING_E1004,
+            WORKING_E1006,
+            WORKING_E1007,
+            WORKING_E1008,
+            WORKING_E1009,
+        )
+    except Exception:
+        # Fallback to local definitions if the shared module isn't available in the
+        # runtime environment (keeps this file robust for standalone use).
+        WORKING_DATA_MODULE = 'dsl.c10_working_with_data'
+        WORKING_E1004 = WORKING_DATA_MODULE + '.e1004_named_tuples'
+        WORKING_E1006 = WORKING_DATA_MODULE + '.e1006_cleaning'
+        WORKING_E1007 = WORKING_DATA_MODULE + '.e1007_manipulation'
+        WORKING_E1008 = WORKING_DATA_MODULE + '.e1008_rescaling'
+        WORKING_E1009 = WORKING_DATA_MODULE + '.e1009_dimensionality_reduction'
 
     for module_const, fnames in grouped.items():
         for fn in fnames:

src/data-scratch-mqtt/data_scratch_mqtt/strategies_library/dynamic_strategy.py

@@ -11,8 +11,7 @@ export function vector_add(v: Array<number>, w: Array<number>) {
 
   const result: number[] = [];
 
-  for (let i = 0; i < v.length; i += 1) {
-    const v_i = v[i];
+  for (const [i, v_i] of v.entries()) {
     const w_i = w[i];
     result.push(v_i + w_i);
   }
@@ -23,8 +22,7 @@ export function vector_add(v: Array<number>, w: Array<number>) {
 export function vector_subtract(v: Array<number>, w: Array<number>) {
   //"""subtracts two vectors componentwise"""
   const result: number[] = [];
-  for (let i = 0; i < v.length; i += 1) {
-    const v_i = v[i];
+  for (const [i, v_i] of v.entries()) {
     const w_i = w[i];
     result.push(v_i - w_i);
   }
@@ -69,8 +67,7 @@ export function vector_mean(vectors: Array<Array<number>>) {
 export function dot(v: Array<number>, w: Array<number>): number {
   //"""v_1 * w_1 + ... + v_n * w_n"""
   let result = 0;
-  for (let i = 0; i < v.length; i += 1) {
-    const v_i = v[i];
+  for (const [i, v_i] of v.entries()) {
     const w_i = w[i];
     result += v_i * w_i;
   }

src/data-scratch-node-library/ts-data-scratch/linear_algebra.ts

@@ -10,8 +10,8 @@ export function bucketize(point: number, bucket_size: number): number {
 
 export function Counter(array: Array<number>) {
     let count = new Map<string, number>();
-    for (let i = 0; i < array.length; i += 1) {
-        const val = array[i].toString();
+    for (const v of array) {
+        const val = v.toString();
         const prev = count.get(val) || 0;
         count.set(val, prev + 1);
     }
@@ -98,8 +98,7 @@ export function de_mean(x: Array<number>) {
     // translate x by subtracting its mean (so the result has mean 0)
     const x_bar = mean(x);
     const result: number[] = [];
-    for (let i = 0; i < x.length; i += 1) {
-        const x_i = x[i];
+    for (const x_i of x) {
         result.push(x_i - x_bar);
     }
     return result

src/data-scratch-node-library/ts-data-scratch/stats.ts

@@ -225,7 +225,7 @@ def analyze_clustering():
 
         # Validate data types
         if not isinstance(points, list):
-            return jsonify({'error': 'data must be a list of points'}), 400
+            return jsonify({'error': ERR_DATA_MUST_BE_LIST}), 400
 
         if not isinstance(assignments, list):
             return jsonify({'error': 'assignments must be a list'}), 400
@@ -318,7 +318,7 @@ def find_optimal_k():
         for k in range(1, max_k + 1):
             k_errors = []
 
-            for run in range(runs_per_k):
+            for _ in range(runs_per_k):
                 assignments, means = k_means(points, k)
                 error = squared_clustering_errors(points, assignments, means)
                 k_errors.append(error)

src/rest-scratch-flask/app/routes/clustering.py

@@ -98,7 +98,7 @@ def train_classifier():
             'message': 'Classifier trained successfully. Use /classify endpoint with the same training data to classify messages.'
         })
 
-    except Exception as e:
+    except Exception:
         logger.exception('Training failed')
         return jsonify({'error': 'Training failed due to an internal error'}), 500
 
@@ -165,7 +165,7 @@ def classify_message():
             'smoothing_parameter': smoothing
         })
 
-    except Exception as e:
+    except Exception:
         # Log full exception server-side but return a generic error to client
         logger.exception('Classification failed')
         return jsonify({'error': 'Classification failed due to an internal error'}), 500
@@ -240,7 +240,7 @@ def batch_classify():
             'smoothing_parameter': smoothing
         })
 
-    except Exception as e:
+    except Exception:
         logger.exception('Batch classification failed')
         return jsonify({'error': 'Batch classification failed due to an internal error'}), 500