Update app.py

app.py

@@ -23,8 +23,8 @@ scaling_factors = {'PROPERTY: Calculated Density (g/cm$^3$)': (5.5, 13.7),
                    'PROPERTY: HV': (107.0, 1183.0),
                    'PROPERTY: YS (MPa)': (62.0, 3416.0)}
 
-input_mapping = {'PROPERTY: BCC/FCC/other': {'BCC': 0, 'FCC': 1, 'OTHER': 2, 'nan': 2},
-                 'PROPERTY: Processing method': {'ANNEAL': 0, 'CAST': 1, 'OTHER': 2, 'POWDER': 3, 'WROUGHT': 4, 'nan': 2},
+input_mapping = {'PROPERTY: BCC/FCC/other': {'BCC': 0, 'FCC': 1, 'OTHER': 2},#, 'nan': 2},
+                 'PROPERTY: Processing method': {'ANNEAL': 0, 'CAST': 1, 'OTHER': 2, 'POWDER': 3, 'WROUGHT': 4},#, 'nan': 2},
                  'PROPERTY: Microstructure': {'B2': 0, 'B2+BCC': 1, 'B2+L12': 2, 'B2+Laves+Sec.': 3, 'B2+Sec.': 4, 'BCC': 5,
                                               'BCC+B2': 6, 'BCC+B2+FCC': 7, 'BCC+B2+FCC+Sec.': 8, 'BCC+B2+L12': 9, 'BCC+B2+Laves': 10,
                                               'BCC+B2+Sec.': 11, 'BCC+BCC': 12, 'BCC+BCC+HCP': 13, 'BCC+BCC+Laves': 14,
@@ -34,22 +34,22 @@ input_mapping = {'PROPERTY: BCC/FCC/other': {'BCC': 0, 'FCC': 1, 'OTHER': 2, 'na
                                               'FCC+BCC+B2': 28, 'FCC+BCC+B2+Sec.': 29, 'FCC+BCC+BCC': 30, 'FCC+BCC+Sec.': 31,
                                               'FCC+FCC': 32, 'FCC+HCP': 33, 'FCC+HCP+Sec.': 34, 'FCC+L12': 35, 'FCC+L12+B2': 36,
                                               'FCC+L12+Sec.': 37, 'FCC+Laves': 38, 'FCC+Laves(C14)': 39, 'FCC+Laves+Sec.': 40,
-                                              'FCC+Sec.': 41, 'L12+B2': 42, 'Laves(C14)+Sec.': 43, 'OTHER': 44, 'nan': 44},
-                 'PROPERTY: Single/Multiphase': {'': 0, 'M': 1, 'S': 2, 'OTHER': 3, 'nan': 3}}
+                                              'FCC+Sec.': 41, 'L12+B2': 42, 'Laves(C14)+Sec.': 43, 'OTHER': 44},#, 'nan': 44},
+                 'PROPERTY: Single/Multiphase': {'': 0, 'M': 1, 'S': 2, 'OTHER': 3}}#, 'nan': 3}}
 
 unique_phase_elements = ['B2', 'BCC', 'FCC', 'HCP', 'L12', 'Laves', 'Laves(C14)', 'Laves(C15)', 'Sec.', 'OTHER']
 
 input_cols = {
     "PROPERTY: Alloy formula": "(PROPERTY: Alloy formula) "
-                               "Recommended alloy formula using proportions representation (i.e. Al0.25 Co1 Fe1 Ni1)",
+                               "Enter alloy formula using proportions representation (i.e. Al0.25 Co1 Fe1 Ni1)",
     "PROPERTY: Single/Multiphase": "(PROPERTY: Single/Multiphase) "
-                                   "Recommended between Single (S), Multiphase (M) and other (OTHER)",
+                                   "Choose between Single (S), Multiphase (M) and other (OTHER)",
     "PROPERTY: BCC/FCC/other": "(PROPERTY: BCC/FCC/other) "
-                               "Recommended microstructure between BCC, FCC and other ",
+                               "Choose between BCC, FCC and other ",
     "PROPERTY: Processing method": "(PROPERTY: Processing method) "
-                                   "Recommended processing method (ANNEAL, CAST, POWDER, WROUGHT or OTHER)",
+                                   "Choose your processing method (ANNEAL, CAST, POWDER, WROUGHT or OTHER)",
     "PROPERTY: Microstructure": "(PROPERTY: Microstructure) "
-                                "Recommended microstructure (SEC means the secondary/tertiary microstructure is not one of FCC, BCC, HCP, L12, B2, Laves, Laves (C14), Laves (C15))",
+                                "Choose the microstructure (SEC means the secondary/tertiary microstructure is not one of FCC, BCC, HCP, L12, B2, Laves, Laves (C14), Laves (C15))",
 }
 
 def process_microstructure(list_phases):
@@ -64,34 +64,25 @@ def write_logs(message, message_type="Prediction"):
     """
     Write logs
     """
-    # with Repository(local_dir="data", clone_from=dataset_url, use_auth_token=WRITE_TOKEN).commit(commit_message="from private", blocking=False):
-    #     with open(dataset_path, "a") as csvfile:
-    #             writer = csv.DictWriter(csvfile, fieldnames=["name", "message", "time"])
-    #             writer.writerow(
-    #                 {"name": message_type, "message": message, "time": str(datetime.now())}
-    #             )
-    print(message)
+    with Repository(local_dir="data", clone_from=dataset_url, use_auth_token=WRITE_TOKEN).commit(commit_message="from private", blocking=False):
+        with open(dataset_path, "a") as csvfile:
+                writer = csv.DictWriter(csvfile, fieldnames=["name", "message", "time"])
+                writer.writerow(
+                    {"name": message_type, "message": message, "time": str(datetime.now())}
+                )
     return 
-
-def fit_outputs(x, hardness_target, ys_target):
-    predictions = predict(x)[0]
-    error_hardness = np.sqrt(np.square(predictions[0]-hardness_target))
-    error_ys = np.sqrt(np.square(predictions[1]-ys_target))
-    print(predictions, hardness_target, ys_target, error_hardness, error_ys)
-    return error_hardness + error_ys
-
-
+    
 def predict(x, request: gr.Request):
     """
     Predict the hardness and yield strength using the ML model. Input data is a dataframe
     """
-    loaded_model = tf.keras.models.load_model("models/hardness_old.h5")
+    loaded_model = tf.keras.models.load_model("hardness.h5")
     print("summary is", loaded_model.summary())
     x = x.replace("", 0)
     x = np.asarray(x).astype("float32")
     y = loaded_model.predict(x)
     y_hardness = y[0][0]
-    # y_ys = y[0][1]
+    y_ys = y[0][1]
     minimum_hardness, maximum_hardness = scaling_factors['PROPERTY: HV']
     minimum_ys, maximum_ys = scaling_factors['PROPERTY: YS (MPa)']
     print("Prediction is ", y)
@@ -100,9 +91,9 @@ def predict(x, request: gr.Request):
         print("MESSAGE")
         print(message)
         res = write_logs(message)
-    interpret_fig_hardness, fig2 = utils.interpret(x)
-    #interpret_fig_ys = utils.interpret(x, 1)
-    return (np.round(y_hardness*(maximum_hardness-minimum_hardness)+minimum_hardness, 2), 12, interpret_fig_hardness)
+    interpret_fig = utils.interpret(x)
+    return (round(y_hardness*(maximum_hardness-minimum_hardness)+minimum_hardness, 2), 12,
+            round(y_ys*(maximum_ys-minimum_ys)+minimum_ys, 2), 12, interpret_fig)
 
 
 def predict_from_tuple(in1, in2, in3, in4, in5, request: gr.Request):
@@ -142,9 +133,8 @@ def predict_from_tuple(in1, in2, in3, in4, in5, request: gr.Request):
     input_df = pd.DataFrame.from_dict(input_dict)
     one_hot = utils.turn_into_one_hot(input_df, input_mapping)
     print("One hot columns are ", one_hot.columns)
-    # return predict(input_df, request)
     return predict(one_hot, request)
-
+    
 
 def predict_inverse(target_hardness, target_yield_strength, request: gr.Request):