Do experiments with lambda

Experiments on no noise data/experiment_burgers_sindy.py

@@ -152,7 +152,7 @@ def hash_term(term):
         arr = np.array([differences_ls_none, time_ls, num_found_eq])
         arr = arr.T
         df = pd.DataFrame(data=arr, columns=['MAE', 'time', 'number_found_eq'])
-        df.to_csv(os.path.join(Path().absolute().parent, "data_burg_sindy", f"{title}.csv"))
+        df.to_csv(os.path.join(Path().absolute().parent, "data_pysindy_burg", f"{title}.csv"))
 
     if print_results:
         print('\nTime for every run, s:')

Experiments on no noise data/experiment_kdv.py

@@ -126,9 +126,9 @@ def hash_term(term):
     grids = np.meshgrid(t, x, indexing='ij')
 
     ''' Parameters of the experiment '''
-    write_csv = False
+    write_csv = True
     print_results = True
-    max_iter_number = 1
+    max_iter_number = 50
     title = 'dfs0'
 
     time_ls = []

Experiments on no noise data/experiment_kdv_sindy.py

@@ -103,9 +103,9 @@ def hash_term(term):
     grids = np.meshgrid(t, x, indexing='ij')
 
     ''' Parameters of the experiment '''
-    write_csv = False
+    write_csv = True
     print_results = True
-    max_iter_number = 1
+    max_iter_number = 50
     title = 'dfs0'
 
     time_ls = []
@@ -154,7 +154,7 @@ def hash_term(term):
         arr = np.array([differences_ls_none, time_ls, num_found_eq])
         arr = arr.T
         df = pd.DataFrame(data=arr, columns=['MAE', 'time', 'number_found_eq'])
-        df.to_csv(os.path.join(Path().absolute().parent, "data_kdv_sindy", f"{title}.csv"))
+        df.to_csv(os.path.join(Path().absolute().parent, "data_pysindy_kdv", f"{title}.csv"))
 
     if print_results:
         print('\nTime for every run, s:')

Experiments on no noise data/experiment_wave.py

@@ -96,9 +96,9 @@ def hash_term(term):
     grids = np.meshgrid(t, x, indexing='ij')
 
     ''' Parameters of the experiment '''
-    write_csv = False
-    print_results = False
-    max_iter_number = 1
+    write_csv = True
+    print_results = True
+    max_iter_number = 50
     title = 'dfs0'
     ''''''
 

Experiments on noised data/noised_burgers.py

@@ -97,10 +97,11 @@ def hash_term(term):
     grids = np.meshgrid(t, x, indexing='ij')
 
     ''' Parameters of the experiment '''
-    write_csv = False
+    write_csv = True
     print_results = True
-    max_iter_number = 50
-    magnitudes = [1. * 1e-5, 1.5 * 1e-5, 2 * 1e-5, 2.5 * 1e-5, 3. * 1e-5, 3.67 * 1e-5] #
+    max_iter_number = 5
+    # magnitudes = [1. * 1e-5, 1.5 * 1e-5, 2 * 1e-5, 2.5 * 1e-5, 3. * 1e-5, 3.67 * 1e-5] #
+    magnitudes = [3. * 1e-5]
 
     terms = [('du/dx1',), ('du/dx2', 'u'), ('u',), ('du/dx2',), ('u', 'du/dx1'), ('du/dx1', 'du/dx2'), ]
     hashed_ls = [hash_term(term) for term in terms]

Experiments on noised data/noised_burgers_sindy.py

@@ -161,7 +161,7 @@ def hash_term(term):
             arr = np.array([differences_ls_none, time_ls, num_found_eq])
             arr = arr.T
             df = pd.DataFrame(data=arr, columns=['MAE', 'time', 'number_found_eq'])
-            df.to_csv(os.path.join(Path().absolute().parent, "data_burg_sindy", f"{title}.csv"))
+            df.to_csv(os.path.join(Path().absolute().parent, "data_pysindy_burg", f"{title}.csv"))
         if print_results:
             print()
             print(f'\nAverage time, s: {sum(time_ls) / len(time_ls):.2f}')

Experiments on noised data/noised_kdv_sindy.py

@@ -112,7 +112,8 @@ def hash_term(term):
     draw_time = []
     draw_avgmae = []
     start_gl = time.time()
-    magnitudes = [1. * 1e-5, 3.5 * 1e-5, 5.5 * 1e-5, 8. * 1e-5, 2.26 * 1e-4]
+    # magnitudes = [1. * 1e-5, 1. * 1e-4, 3.5 * 1e-5, 5.5 * 1e-5, 8. * 1e-5, 2.26 * 1e-4]
+    magnitudes = [1. * 1e-4]
     for magnitude in magnitudes:
         title = f'dfs{magnitude}'
 
@@ -162,7 +163,7 @@ def hash_term(term):
             arr = np.array([differences_ls_none, time_ls, num_found_eq])
             arr = arr.T
             df = pd.DataFrame(data=arr, columns=['MAE', 'time', 'number_found_eq'])
-            df.to_csv(os.path.join(Path().absolute().parent, "data_kdv_sindy", f"{title}.csv"))
+            df.to_csv(os.path.join(Path().absolute().parent, "data_pysindy_kdv", f"{title}.csv"))
 
             if print_results:
                 print()

Experiments on noised data/noised_wave.py

@@ -100,15 +100,20 @@ def hash_term(term):
     coefficients[1] = 0.
 
     ''' Parameters of the experiment '''
-    write_csv = False
+    write_csv = True
     print_results = True
     max_iter_number = 50
-    magnitudes = [1. * 1e-2]
+    magnitudes = [2. * 1e-5, 2.5 * 1e-5, 3. * 1e-5, 3.2 * 1e-5, 3.47 * 1e-5]
+    # magnitudes = [3.47 * 1e-5]
 
     draw_not_found = []
     draw_time = []
     draw_avgmae = []
     start_gl = time.time()
+    not_found_ls = []
+    # string = "0.04073797307153838 * d^2u/dx2^2{power: 1.0} + 0.0014821321520873156 * du/dx1{power: 1.0} + 0.034797130718506576 = d^2u/dx1^2{power: 1.0}"
+    # difference_ls = find_diff_str(string, coefficients)
+
     for magnitude in magnitudes:
         title = f'dfs{magnitude}'
 
@@ -146,15 +151,18 @@ def hash_term(term):
                 differences_ls.append(min(difference_ls))
                 differences_ls_none.append(min(difference_ls))
                 mean_diff_ls += difference_ls
+                print(f"Num. eq. found: {len(difference_ls)}")
             else:
                 differences_ls_none.append(None)
+                print(f"Num. eq. found: 0")
 
             num_found_eq.append(len(difference_ls))
             print('Overall time is:', time1)
             print(f'Iteration processed: {i+1}/{max_iter_number}\n')
             i += 1
             time_ls.append(time1)
 
+        not_found_ls.append(num_found_eq.count(0))
         if write_csv:
             arr = np.array([differences_ls_none, time_ls, num_found_eq])
             arr = arr.T
@@ -182,24 +190,26 @@ def hash_term(term):
         draw_time.append(sum(time_ls) / len(time_ls))
 
     end_gl = time.time()
-    print(f"Overall time: {end_gl - start_gl:.2f}, s.")
-    plt.title("SymNet")
-    plt.plot(magnitudes, draw_not_found, linewidth=2, markersize=9, marker='o')
-    plt.ylabel("No. runs with not found eq.")
-    plt.xlabel("Magnitude value")
-    plt.grid()
-    plt.show()
-
-    plt.plot(magnitudes, draw_time, linewidth=2, markersize=9, marker='o')
-    plt.title("SymNet")
-    plt.ylabel("Time, s.")
-    plt.xlabel("Magnitude value")
-    plt.grid()
-    plt.show()
-
-    plt.plot(magnitudes, draw_avgmae, linewidth=2, markersize=9, marker='o')
-    plt.title("SymNet")
-    plt.ylabel("Average MAE")
-    plt.xlabel("Magnitude value")
-    plt.grid()
-    plt.show()
+    print(f"Overall time: {(end_gl - start_gl) / 3600:.2f}, h.")
+    print(f"Runs where eq was not found for each magn: {not_found_ls}")
+    # print(f"Overall time: {end_gl - start_gl:.2f}, s.")
+    # plt.title("Original")
+    # plt.plot(magnitudes, draw_not_found, linewidth=2, markersize=9, marker='o')
+    # plt.ylabel("No. runs with not found eq.")
+    # plt.xlabel("Magnitude value")
+    # plt.grid()
+    # plt.show()
+    #
+    # plt.plot(magnitudes, draw_time, linewidth=2, markersize=9, marker='o')
+    # plt.title("Original")
+    # plt.ylabel("Time, s.")
+    # plt.xlabel("Magnitude value")
+    # plt.grid()
+    # plt.show()
+    #
+    # plt.plot(magnitudes, draw_avgmae, linewidth=2, markersize=9, marker='o')
+    # plt.title("Original")
+    # plt.ylabel("Average MAE")
+    # plt.xlabel("Magnitude value")
+    # plt.grid()
+    # plt.show()

symnet/initcoefficients.py

@@ -95,7 +95,7 @@ def closure():
 
 def select_model(input_names, left_pool, u, derivs, shape, additional_tokens):
     models, losses, left_sides = [], [], []
-    info = ModelsInfo()
+    # info = ModelsInfo()
     for left_side_name in left_pool:
         for sparsity in [0.001, 0.0000001]:
             m_input_names, idx = clean_names(left_side_name, input_names)
@@ -106,9 +106,9 @@ def select_model(input_names, left_pool, u, derivs, shape, additional_tokens):
             models.append(model)
             left_sides.append(left_side_name)
 
-            info.selection_info(model, last_loss, sparsity, left_side_name)
+            # info.selection_info(model, last_loss, sparsity, left_side_name)
 
-    info.print_best()
+    # info.print_best()
     idx = losses.index(min(losses))
     return models[idx], left_sides[idx]
 
@@ -134,12 +134,15 @@ def get_csym_tsym(u, derivs, shape, input_names, pool_names, additional_tokens=N
     """
     Can process only one variable! (u)
     """
+    # TODO: SymNet имеет 4 todo (+, pool_terms, preproc_input)
+
+    # TODO: если в левой части e.g. d^2u/dx2^2, то как получить в правой слагаемое d^2u/dx2^2 * u?
 
     left_pool = get_left_pool(max_deriv_order)
-    model, left_side_name = select_model(input_names, left_pool, u, derivs, shape, sparsity, additional_tokens)
+    model, left_side_name = select_model(input_names, left_pool, u, derivs, shape, additional_tokens)
     tsym, csym = model.coeffs(calprec=16)
     # save_fig(csym)
     pool_sym_ls = cast_to_symbols(pool_names)
+
     csym_pool_ls = get_csym_pool(tsym, csym, pool_sym_ls, left_side_name)
-    # save_fig(np.array(csym_pool_ls), add_left=False)
     return dict(zip(pool_sym_ls, csym_pool_ls)), pool_sym_ls