Update readme and code

README.md

@@ -239,8 +239,7 @@ The structure of the file is:
     * error for sample's parameters: distance between real and predicted sample's parameter value.
 * **Original_misclassified.txt:** file (.txt format) produced copying and pasting the logs produced in [retrain.py](python/retrain.py)
  when option *--print_misclassified_images* is set to *True*. It is used in 
- [misclassified_images.py](python/misclassified_images.py) to reclassify images.
-* Inside **Sphere** folder, with *results.csv* and *suggest.csv* files, we can also find the histograms of radius error. 
+ [misclassified_images.py](python/misclassified_images.py) to reclassify images. 
 
 ### imgs
 It contains two folders (one for each particle model). Each one of them have two folders: one with **simulated** scattered 
@@ -264,7 +263,17 @@ particles and the type of regression it has been applied in it.
 The number in the name specifies the cluster for which that regression model applies. e.g. Sphere_rf_cluster_0.pkl 
 applies to *"bad guinier's"* scattered images (cluster 0).
 
+
 ## Datasets
 All the datasets, which with we have generated the master *results.csv* files located in [doc_files](doc_files), are in:
        
-    /home/dpt/sci_share/ScatterImage/fernandez-ruiz/
\ No newline at end of file
+    /home/dpt/sci_share/ScatterImage/fernandez-ruiz/
+    
+Besides, we can fin a folder **results_logs**. In it, we have again two folders (one for each particle model). In each 
+one of them we can find several folders:
+* **regression_randForest_errorRadius_wholeDataset:** inside **Sphere** folder, we can find the histograms of predicted 
+radius error when applying a regression (*random forest*) to the images inside [results.csv](doc_files/Sphere/results.csv)
+* **Contribution of params:** images for selecting which sample parameters are relevant in the final images. For doing so,
+we generate images letting all the parameters fixed except the one we are studying.
+* **ImagesDistribution:**  plots the distribution of images in [results.csv](doc_files/Sphere/results.csv) based on their 
+radius, CNN prediction, wavelength and distance. In this way we can figure out how to obtain Guinier, one ring images...

python/GUI_SANS.py

@@ -208,7 +208,8 @@ start = datetime.datetime.now()
 # ------------------------ VARIABLE DEFINITION ------------------------
 # INTERNAL VARIABLES
 reg_model_type = "rf"  # random forest
-database_path = "/home/dpt/fernandez-ruiz/TF_Results/GUI/"
+database_path = "/users/fernandez-ruiz/scatteringimage/models/Sphere/"  # path where output_graph and output_labels are
+    # (CNN model files from retrain.py), master results.csv and regression models are (in a folder whose name is the type of regression model)
 GUI_img_path = "GUI_imgs"
 results_file = "results.csv"
 tmp_folder = "tmp"
@@ -226,7 +227,7 @@ print("SCATTERED MODEL chosen: %s" % (scatter_model.upper()))  # print user deci
 if scatter_model == "Sphere":
     sample_params_list = ["radius"]
 elif scatter_model == "Core-Shell Sphere":
-    sample_params_list = ["radius", "shell"]
+    sample_params_list = ["radius", "rhocore", "rhoshell"]
 print("-------------------------------------------------------\n")
 
 #   Categ searched
@@ -332,7 +333,7 @@ for param in categ_param:
 
 # ------------------------ DATABASE INFO ------------------------
 # We have a master file with all possible combinations of sample and instrument parameters. And the cluster prediction for each one
-database_df = pd.read_csv(join(database_path, scatter_model, results_file))
+database_df = pd.read_csv(join(database_path, results_file))
 # Extract unique values for each column
 distinct_instr_values, reg_columns = distinct_values(database_df, categ_param, predicted_cluster)
 # Our regression model differentiates between categ and non categorical variables. Only bg and mean predict are
@@ -362,9 +363,9 @@ reg_X = X_non_categ + reg_X
 # ------------------------ REGRESSION MODEL ------------------------
 # Load regression model. We have a reg model for each cluster: e.g. Sphere_rf_cluster_0.pkl, Sphere_rf_cluster_1.pkl,...
 # Extract the path of the reg models files
-reg_files = [join(database_path, scatter_model, reg_model_type, f)
-             for f in os.listdir(join(database_path, scatter_model, reg_model_type))
-             if os.path.isfile(join(database_path, scatter_model, reg_model_type, f))]
+reg_files = [join(database_path, reg_model_type, f)
+             for f in os.listdir(join(database_path, reg_model_type))
+             if os.path.isfile(join(database_path, reg_model_type, f))]
 reg_files.sort()  # Sort them by name
 reg_list = []
 for reg_model in reg_files:  # append models objects in a script
@@ -443,8 +444,8 @@ for idx, row in suggest_data.iterrows():
 
 # We apply label_image to suggested images we have just created. In this way, we classify them into folders with name of clusters
 subprocess.run(["python", join(python_script_path, "label_classify_image_folder.py"),
-                "--dir", join(database_path, tmp_folder), "--graph", join(database_path, scatter_model, "output_graph.pb"),
-                "--labels", join(database_path, scatter_model, "output_labels.txt"),
+                "--dir", join(database_path, tmp_folder), "--graph", join(database_path, "output_graph.pb"),
+                "--labels", join(database_path, "output_labels.txt"),
                 "--input_layer", "Placeholder", "--output_layer", "final_result",
                 "--results_path", join(database_path, tmp_folder, results_file),
                 "--sample_params_list", *sample_params_list, "--silence", "True"])

python/label_classify_image_folder.py

@@ -135,8 +135,8 @@ def obtain_parameter_val(file_name, parameter):
 
 
 if __name__ == "__main__":
-  input_height = 224  #299
-  input_width = 224  #299
+  input_height = 299 #224  #299
+  input_width = 299 #224  #299
   input_mean = 0
   input_std = 255
   input_layer = "Placeholder"

python/main_SANS.py

@@ -38,7 +38,7 @@ tmp_folder = "tmp"  # tmp file. It is going to be created inside 'img_path'
 save_img_sug_folder = "Classif_by_categ"  # folder where we are going to create suggestes images. It is going to be created inside 'img_path'
 python_script_path = "/users/fernandez-ruiz/scatteringimage/python/"  # Where are python scripts. Remember that all of them should be in the same folder
 matlab_path = "/users/fernandez-ruiz/scatteringimage/matlab/"  # Where are matlab scripts. Remember that all of them should be in the same folder
-retrain_model_path = "/home/dpt/fernandez-ruiz/TF_Results/GUI_Core/"  # "output_labels.py", "output_graph.pb" should be in this folder. (files from retrain.py)
+retrain_model_path = "/users/fernandez-ruiz/scatteringimage/models/Sphere/"  # "output_labels.py", "output_graph.pb" should be in this folder. (files from retrain.py)
 categ_search = "1"  # [0: bad guinier, 1: good guinier, 2: one ring, 3: two or three rings, 4: four or five rings,
                     # 5: more than five rings, 6: bad background images, 7: background image]
 num_clusters = "8"  # number of clusters we are going to study

python/multiv_multip_regression.py

@@ -239,8 +239,8 @@ if __name__ == "__main__":
     # results_path = "/home/dpt/fernandez-ruiz/sim/sim_data/Sphere/log_image/20190531_resize/results.csv"
     # suggest_path = "/home/dpt/fernandez-ruiz/sim/sim_data/Sphere/log_image/20190531_resize/suggest5.csv"
     # matlab_path = "/users/fernandez-ruiz/scatteringimage/matlab/"
-    # retrain_model_path = "/home/dpt/fernandez-ruiz/TF_Results/sphere_7_improved/"  # "output_labels.py", "output_graph.pb" should be in this folder. (files from retrain.py)
     # python_script_path = "/users/fernandez-ruiz/scatteringimage/python/"
+    # retrain_model_path = "users/fernandez-ruiz/scatteringimage/models/Sphere/"  # "output_labels.py", "output_graph.pb" should be in this folder. (files from retrain.py)
     # tmp_folder = "/home/dpt/fernandez-ruiz/sim/sim_data/Sphere/log_image/20190531_resize/tmp"
     # scatter_model = "Sphere"  # Define the model
     # categ_search = 1
@@ -322,9 +322,9 @@ if __name__ == "__main__":
         # Save regression model
         if save_reg_model == "True":
             model_name = scatter_model + "_" + reg_type + "_cluster" + str(i) + ".pkl"  # Model name definition
-            if not os.path.isdir(join(retrain_model_path, scatter_model, reg_type)):  # If the dir does not exists...
-                os.makedirs(join(retrain_model_path, scatter_model, reg_type), exist_ok=True)  # create it
-            joblib_file = join(retrain_model_path, scatter_model, reg_type, model_name)
+            if not os.path.isdir(join(retrain_model_path, reg_type)):  # If the dir does not exists...
+                os.makedirs(join(retrain_model_path, reg_type), exist_ok=True)  # create it
+            joblib_file = join(retrain_model_path, reg_type, model_name)
             joblib.dump(regr[i], joblib_file)  # save model
 
         # Plot summary of models