Update of project documentation; Add of scripts to run with custom min max file

README.md

@@ -26,13 +26,15 @@ You can also specify metric you want to compute and image step to avoid some ima
 python generate_all_data.py --metric mscn --step 50
 ```
 
+- **step** : keep only image if image id % 50 == 0 (assumption is that keeping spaced data will let model better fit).
+
 ## How to use
 
 ### Multiple folders and scripts are availables :
 
 
 - **fichiersSVD_light/\*** : all scene files information (zones of each scene, SVD descriptor files information and so on...).
-- **models/*.py** : all models developed to predict noise in image.
+- **train_model.py** : script which is used to run specific model available.
 - **data/\*** : folder which will contain all *.train* & *.test* files in order to train model.
 - **saved_models/*.joblib** : all scikit learn models saved.
 - **models_info/*** : all markdown files generated to get quick information about model performance and prediction. This folder contains also **model_comparisons.csv** obtained after running runAll_maxwell.sh script.
@@ -51,7 +53,7 @@ Two scripts can be used for generating data in order to fit model :
 ```
 python generate_data_model.py --help
 
-python generate_data_model.py --output xxxx --interval 0,20  --kind svdne --scenes "A, B, D" --zones "0, 1, 2" --percent 0.7 --sep : --rowindex 1
+python generate_data_model.py --output xxxx --interval 0,20  --kind svdne --scenes "A, B, D" --zones "0, 1, 2" --percent 0.7 --sep : --rowindex 1 --custom custom_min_max_filename
 ```
 
 Parameters explained :
@@ -63,37 +65,36 @@ Parameters explained :
 - **percent** : percent of data amount of zone to take (choose randomly) of zone
 - **sep** : output csv file seperator used
 - **rowindex** : if 1 then row will be like that 1:xxxxx, 2:xxxxxx, ..., n:xxxxxx
+- **custom** : specify if you want your data normalized using interval and not the whole singular values vector. If it is, the value of this parameter is the output filename which will store the min and max value found. This file will be usefull later to make prediction with model (optional parameter).
 
 ### Train model
 
 This is an example of how to train a model
 
 ```bash
-python models/xxxxx.py --data 'data/xxxxx.train' --output 'model_file_to_save'
+python train_model.py --data 'data/xxxxx.train' --output 'model_file_to_save' --choice 'model_choice'
 ```
 
+Expected values for the **choice** parameter are ['svm_model', 'ensemble_model', 'ensemble_model_v2'].
+
 ### Predict image using model
 
 Now we have a model trained, we can use it with an image as input :
 
 ```bash
-python metrics_predictions/predict_noisy_image_svd_lab.py --image path/to/image.png --interval "x,x" --model saved_models/xxxxxx.joblib --mode 'svdn'
+python predict_noisy_image_svd.py --image path/to/image.png --interval "x,x" --model saved_models/xxxxxx.joblib --metric 'lab' --mode 'svdn' --custom 'min_max_filename'
 ```
 
+- **metric** : metric choice need to be one of the listed above.
+- **custom** : specify filename with custom min and max from your data interval. This file was generated using **custom** parameter of one of the **generate_data_model\*.py** script (optional parameter).
+
 The model will return only 0 or 1 :
 - 1 means noisy image is detected.
 - 0 means image seem to be not noisy.
 
-You can also use other specific metric
-
-```bash
-python metrics_predictions/predict_noisy_image_svd_mscn.py --image path/to/image.png --interval "x,x" --model saved_models/xxxxxx.joblib --mode 'svdn'
-```
-
-All SVD metrics you developed need :
-- Name added into *metric_choices* global array variable of **generate_all_data.py** file.
-- A specification of how you compute the metric into generate_data_svd method of **generate_all_data.py** file.
-- A prediction script into **metrics_predictions** folder. Name need to follow this rule : *predict_noisy_image_svd_xxxx.py*
+All SVD metrics developed need :
+- Name added into *metric_choices_labels* global array variable of **modules/utils/config.py** file.
+- A specification of how you compute the metric into *get_svd_data* method of **modules/utils/data_type.py** file.
 
 ### Predict scene using model
 
@@ -112,7 +113,7 @@ Just use --help option to get more information.
 
 ### Simulate model on scene
 
-All scripts named **predict_seuil_expe\*.py** are used to simulate model prediction during rendering process.
+All scripts named **predict_seuil_expe\*.py** are used to simulate model prediction during rendering process. Do not forget the **custom** parameter filename if necessary.
 
 Once you have simulation done. Checkout your **threshold_map/%MODEL_NAME%/simulation\_curves\_zones\_\*/** folder and use it with help of **display_simulation_curves.py** script.
 
@@ -139,7 +140,7 @@ Parameters list :
 Main objective of this project is to predict as well as a human the noise perception on a photo realistic image. Human threshold is available from training data. So a script was developed to give the predicted treshold from model and compare predicted treshold from the expected one.
 
 ```bash
-python predict_seuil_expe.py --interval "x,x" --model 'saved_models/xxxx.joblib' --mode ["svd", "svdn", "svdne"] --metric ['lab', 'mscn', ...] --limit_detection xx
+python predict_seuil_expe.py --interval "x,x" --model 'saved_models/xxxx.joblib' --mode ["svd", "svdn", "svdne"] --metric ['lab', 'mscn', ...] --limit_detection xx --custom 'custom_min_max_filename'
 ```
 
 Parameters list :
@@ -147,6 +148,7 @@ Parameters list :
 - **interval** : the interval of data you want to use from SVD vector.
 - **mode** : kind of data ['svd', 'svdn', 'svdne']; not normalize, normalize vector only and normalize together.
 - **limit_detection** : number of not noisy images found to stop and return threshold (integer).
+- **custom** : custom filename where min and max values are stored (optional parameter).
 
 ### Display model performance information
 

generateAndTrain_maxwell.sh

@@ -46,7 +46,6 @@ for counter in {0..4}; do
 
                 FILENAME="data/data_maxwell_N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}"
                 MODEL_NAME="${model}_N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}"
-                CUSTOM_MIN_MAX_FILENAME="N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}_min_max"
 
                 echo $FILENAME
 
@@ -55,10 +54,10 @@ for counter in {0..4}; do
 
                     echo "${MODEL_NAME} results already generated..."
                 else
-                    python generate_data_model_random_maxwell.py --output ${FILENAME} --interval "${start},${end}" --kind ${mode} --metric ${metric} --scenes "${scenes}" --nb_zones "${nb_zones}" --percent 1 --sep ';' --rowindex '0' --custom ${CUSTOM_MIN_MAX_FILENAME}
+                    python generate_data_model_random_maxwell.py --output ${FILENAME} --interval "${start},${end}" --kind ${mode} --metric ${metric} --scenes "${scenes}" --nb_zones "${nb_zones}" --percent 1 --sep ';' --rowindex '0'
                     python train_model.py --data ${FILENAME} --output ${MODEL_NAME} --choice ${model}
 
-                    #python predict_seuil_expe_maxwell.py --interval "${start},${end}" --model "saved_models/${MODEL_NAME}.joblib" --mode "${mode}" --metric ${metric} --limit_detection '2' --custom ${CUSTOM_MIN_MAX_FILENAME}
+                    #python predict_seuil_expe_maxwell.py --interval "${start},${end}" --model "saved_models/${MODEL_NAME}.joblib" --mode "${mode}" --metric ${metric} --limit_detection '2'
                     python save_model_result_in_md_maxwell.py --interval "${start},${end}" --model "saved_models/${MODEL_NAME}.joblib" --mode "${mode}" --metric ${metric}
                 fi
             done

generateAndTrain_maxwell_custom.sh

@@ -0,0 +1,74 @@
+#! bin/bash
+
+if [ -z "$1" ]
+  then
+    echo "No argument supplied"
+    echo "Need of vector size"
+    exit 1
+fi
+
+if [ -z "$2" ]
+  then
+    echo "No argument supplied"
+    echo "Need of metric information"
+    exit 1
+fi
+
+result_filename="models_info/models_comparisons.csv"
+VECTOR_SIZE=200
+size=$1
+metric=$2
+
+# selection of four scenes (only maxwell)
+scenes="A, D, G, H"
+
+half=$(($size/2))
+start=-$half
+for counter in {0..4}; do
+    end=$(($start+$size))
+
+    if [ "$end" -gt "$VECTOR_SIZE" ]; then
+        start=$(($VECTOR_SIZE-$size))
+        end=$(($VECTOR_SIZE))
+    fi
+
+    if [ "$start" -lt "0" ]; then
+        start=$((0))
+        end=$(($size))
+    fi
+
+    for nb_zones in {4,6,8,10,12,14}; do
+
+        echo $start $end
+
+        for mode in {"svd","svdn","svdne"}; do
+            for model in {"svm_model","ensemble_model","ensemble_model_v2"}; do
+
+                FILENAME="data/data_maxwell_N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}"
+                MODEL_NAME="${model}_N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}"
+                CUSTOM_MIN_MAX_FILENAME="N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}_min_max"
+
+                echo $FILENAME
+
+                # only compute if necessary (perhaps server will fall.. Just in case)
+                if grep -q "${MODEL_NAME}" "${result_filename}"; then
+
+                    echo "${MODEL_NAME} results already generated..."
+                else
+                    python generate_data_model_random_maxwell.py --output ${FILENAME} --interval "${start},${end}" --kind ${mode} --metric ${metric} --scenes "${scenes}" --nb_zones "${nb_zones}" --percent 1 --sep ';' --rowindex '0' --custom ${CUSTOM_MIN_MAX_FILENAME}
+                    python train_model.py --data ${FILENAME} --output ${MODEL_NAME} --choice ${model}
+
+                    #python predict_seuil_expe_maxwell.py --interval "${start},${end}" --model "saved_models/${MODEL_NAME}.joblib" --mode "${mode}" --metric ${metric} --limit_detection '2' --custom ${CUSTOM_MIN_MAX_FILENAME}
+                    python save_model_result_in_md_maxwell.py --interval "${start},${end}" --model "saved_models/${MODEL_NAME}.joblib" --mode "${mode}" --metric ${metric}
+                fi
+            done
+        done
+    done
+
+    if [ "$counter" -eq "0" ]; then
+        start=$(($start+50-$half))
+    else
+        start=$(($start+50))
+    fi
+
+done

generate_data_model_r.py

@@ -0,0 +1,277 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Sep 14 21:02:42 2018
+
+@author: jbuisine
+"""
+
+from __future__ import print_function
+import sys, os, getopt
+import numpy as np
+import random
+import time
+import json
+
+from PIL import Image
+from ipfml import processing, metrics
+
+from modules.utils import config as cfg
+
+# getting configuration information
+config_filename         = cfg.config_filename
+zone_folder             = cfg.zone_folder
+min_max_filename        = cfg.min_max_filename_extension
+
+# define all scenes values
+scenes_list             = cfg.scenes_names
+scenes_indexes          = cfg.scenes_indices
+choices                 = cfg.normalization_choices
+path                    = cfg.dataset_path
+zones                   = cfg.zones_indices
+seuil_expe_filename     = cfg.seuil_expe_filename
+
+metric_choices          = cfg.metric_choices_labels
+output_data_folder      = cfg.output_data_folder
+custom_min_max_folder   = cfg.min_max_custom_folder
+min_max_ext             = cfg.min_max_filename_extension
+zones_indices           = cfg.zones_indices
+
+generic_output_file_svd = '_random.csv'
+
+min_value_interval = sys.maxsize
+max_value_interval = 0
+
+def construct_new_line(path_seuil, interval, line, norm, sep, index):
+    begin, end = interval
+
+    line_data = line.split(';')
+    seuil = line_data[0]
+    metrics = line_data[begin+1:end+1]
+
+    metrics = [float(m) for m in metrics]
+
+    # TODO : check if it's always necessary to do that (loss of information for svd)
+    if norm:
+        metrics = processing.normalize_arr_with_range(metrics, min_value_interval, max_value_interval)
+
+    with open(path_seuil, "r") as seuil_file:
+        seuil_learned = int(seuil_file.readline().strip())
+
+    if seuil_learned > int(seuil):
+        line = '1'
+    else:
+        line = '0'
+
+    for idx, val in enumerate(metrics):
+        if index:
+            line += " " + str(idx + 1)
+        line += sep
+        line += str(val)
+    line += '\n'
+
+    return line
+
+def get_min_max_value_interval(_filename, _interval, _choice, _metric):
+
+    global min_value_interval, max_value_interval
+
+    scenes = os.listdir(path)
+
+    # remove min max file from scenes folder
+    scenes = [s for s in scenes if min_max_filename not in s]
+
+    for id_scene, folder_scene in enumerate(scenes):
+
+        # only take care of maxwell scenes
+        if folder_scene in scenes_list:
+
+            scene_path = os.path.join(path, folder_scene)
+
+            zones_folder = []
+            # create zones list
+            for index in zones:
+                index_str = str(index)
+                if len(index_str) < 2:
+                    index_str = "0" + index_str
+                zones_folder.append("zone"+index_str)
+
+            # shuffle list of zones (=> randomly choose zones)
+            random.shuffle(zones_folder)
+
+            for id_zone, zone_folder in enumerate(zones_folder):
+                zone_path = os.path.join(scene_path, zone_folder)
+                data_filename = _metric + "_" + _choice + generic_output_file_svd
+                data_file_path = os.path.join(zone_path, data_filename)
+
+                # getting number of line and read randomly lines
+                f = open(data_file_path)
+                lines = f.readlines()
+
+                counter = 0
+                # check if user select current scene and zone to be part of training data set
+                for line in lines:
+
+                    begin, end = _interval
+
+                    line_data = line.split(';')
+                    metrics = line_data[begin+1:end+1]
+                    metrics = [float(m) for m in metrics]
+
+                    min_value = min(metrics)
+                    max_value = max(metrics)
+
+                    if min_value < min_value_interval:
+                        min_value_interval = min_value
+
+                    if max_value > max_value_interval:
+                        max_value_interval = max_value
+
+                    counter += 1
+
+
+def generate_data_model(_filename, _interval, _choice, _metric, _scenes = scenes_list, _zones = zones_indices, _percent = 1, _norm = False, _sep=':', _index=True):
+
+    output_train_filename = _filename + ".train"
+    output_test_filename = _filename + ".test"
+
+    if not '/' in output_train_filename:
+        raise Exception("Please select filename with directory path to save data. Example : data/dataset")
+
+    # create path if not exists
+    if not os.path.exists(output_data_folder):
+        os.makedirs(output_data_folder)
+
+    train_file = open(output_train_filename, 'w')
+    test_file = open(output_test_filename, 'w')
+
+    scenes = os.listdir(path)
+
+    # remove min max file from scenes folder
+    scenes = [s for s in scenes if min_max_filename not in s]
+
+    for id_scene, folder_scene in enumerate(scenes):
+
+        # only take care of maxwell scenes
+        if folder_scene in scenes_list:
+
+            scene_path = os.path.join(path, folder_scene)
+
+            zones_folder = []
+            # create zones list
+            for index in zones:
+                index_str = str(index)
+                if len(index_str) < 2:
+                    index_str = "0" + index_str
+                zones_folder.append("zone"+index_str)
+
+            for id_zone, zone_folder in enumerate(zones_folder):
+                zone_path = os.path.join(scene_path, zone_folder)
+                data_filename = _metric + "_" + _choice + generic_output_file_svd
+                data_file_path = os.path.join(zone_path, data_filename)
+
+                # getting number of line and read randomly lines
+                f = open(data_file_path)
+                lines = f.readlines()
+
+                num_lines = len(lines)
+
+                lines_indexes = np.arange(num_lines)
+                random.shuffle(lines_indexes)
+
+                path_seuil = os.path.join(zone_path, seuil_expe_filename)
+
+                counter = 0
+                # check if user select current scene and zone to be part of training data set
+                for index in lines_indexes:
+                    line = construct_new_line(path_seuil, _interval, lines[index], _norm, _sep, _index)
+
+                    percent = counter / num_lines
+
+                    if id_zone in _zones and folder_scene in _scenes and percent <= _percent:
+                        train_file.write(line)
+                    else:
+                        test_file.write(line)
+
+                    counter += 1
+
+                f.close()
+
+    train_file.close()
+    test_file.close()
+
+
+def main():
+
+    p_custom = False
+
+    if len(sys.argv) <= 1:
+        print('python generate_data_model.py --output xxxx --interval 0,20  --kind svdne --metric lab --scenes "A, B, D" --zones "1, 2, 3, 4" --percent 0.7 --sep : --rowindex 1 --custom min_max_filename')
+        sys.exit(2)
+    try:
+        opts, args = getopt.getopt(sys.argv[1:], "ho:i:k:s:z:p:r:c", ["help=", "output=", "interval=", "kind=", "metric=","scenes=", "zones=", "percent=", "sep=", "rowindex=", "custom="])
+    except getopt.GetoptError:
+        # print help information and exit:
+        print('python generate_data_model.py --output xxxx --interval 0,20  --kind svdne --metric lab --scenes "A, B, D" --zones "1, 2, 3, 4" --percent 0.7 --sep : --rowindex 1 --custom min_max_filename')
+        sys.exit(2)
+    for o, a in opts:
+        if o == "-h":
+            print('python generate_data_model.py --output xxxx --interval 0,20  --kind svdne --metric lab --scenes "A, B, D" --zones "1, 2, 3, 4" --percent 0.7 --sep : --rowindex 1 --custom min_max_filename')
+
+            sys.exit()
+        elif o in ("-o", "--output"):
+            p_filename = a
+        elif o in ("-i", "--interval"):
+            p_interval = list(map(int, a.split(',')))
+        elif o in ("-k", "--kind"):
+            p_kind = a
+        elif o in ("-m", "--metric"):
+            p_metric = a
+        elif o in ("-s", "--scenes"):
+            p_scenes = a.split(',')
+        elif o in ("-z", "--zones"):
+            if ',' in a:
+                p_zones = list(map(int, a.split(',')))
+            else:
+                p_zones = [a.strip()]
+        elif o in ("-p", "--percent"):
+            p_percent = float(a)
+        elif o in ("-s", "--sep"):
+            p_sep = a
+        elif o in ("-r", "--rowindex"):
+            if int(a) == 1:
+                p_rowindex = True
+            else:
+                p_rowindex = False
+        elif o in ("-c", "--custom"):
+            p_custom = a
+        else:
+            assert False, "unhandled option"
+
+    # getting scenes from indexes user selection
+    scenes_selected = []
+
+    for scene_id in p_scenes:
+        index = scenes_indexes.index(scene_id.strip())
+        scenes_selected.append(scenes_list[index])
+
+    # find min max value if necessary to renormalize data
+    if p_custom:
+        get_min_max_value_interval(p_filename, p_interval, p_kind, p_metric)
+
+        # write new file to save
+        if not os.path.exists(custom_min_max_folder):
+            os.makedirs(custom_min_max_folder)
+
+        min_max_folder_path = os.path.join(os.path.dirname(__file__), custom_min_max_folder)
+        min_max_filename_path = os.path.join(min_max_folder_path, p_custom)
+
+        with open(min_max_filename_path, 'w') as f:
+            f.write(str(min_value_interval) + '\n')
+            f.write(str(max_value_interval) + '\n')
+
+    # create database using img folder (generate first time only)
+    generate_data_model(p_filename, p_interval, p_kind, p_metric, scenes_selected, p_zones, p_percent, p_custom, p_sep, p_rowindex)
+
+if __name__== "__main__":
+    main()

generate_data_model_random.py

@@ -14,8 +14,7 @@ import time
 import json
 
 from PIL import Image
-from ipfml import processing
-from ipfml import metrics
+from ipfml import processing, metrics
 
 from modules.utils import config as cfg
 
@@ -33,16 +32,28 @@ zones                   = cfg.zones_indices
 seuil_expe_filename     = cfg.seuil_expe_filename
 
 metric_choices          = cfg.metric_choices_labels
-
 output_data_folder      = cfg.output_data_folder
+custom_min_max_folder   = cfg.min_max_custom_folder
+min_max_ext             = cfg.min_max_filename_extension
+
+generic_output_file_svd = '_random.csv'
+
+min_value_interval = sys.maxsize
+max_value_interval = 0
 
-def construct_new_line(path_seuil, interval, line, sep, index):
+def construct_new_line(path_seuil, interval, line, norm, sep, index):
     begin, end = interval
 
     line_data = line.split(';')
     seuil = line_data[0]
     metrics = line_data[begin+1:end+1]
 
+    metrics = [float(m) for m in metrics]
+
+    # TODO : check if it's always necessary to do that (loss of information for svd)
+    if norm:
+        metrics = processing.normalize_arr_with_range(metrics, min_value_interval, max_value_interval)
+
     with open(path_seuil, "r") as seuil_file:
         seuil_learned = int(seuil_file.readline().strip())
 
@@ -55,12 +66,71 @@ def construct_new_line(path_seuil, interval, line, sep, index):
         if index:
             line += " " + str(idx + 1)
         line += sep
-        line += val
+        line += str(val)
     line += '\n'
 
     return line
 
-def generate_data_model(_filename, _interval, _choice, _metric, _scenes = scenes_list, _nb_zones = 4, _percent = 1, _sep=':', _index=True):
+def get_min_max_value_interval(_filename, _interval, _choice, _metric):
+
+    global min_value_interval, max_value_interval
+
+    scenes = os.listdir(path)
+
+    # remove min max file from scenes folder
+    scenes = [s for s in scenes if min_max_filename not in s]
+
+    for id_scene, folder_scene in enumerate(scenes):
+
+        # only take care of maxwell scenes
+        if folder_scene in scenes_list:
+
+            scene_path = os.path.join(path, folder_scene)
+
+            zones_folder = []
+            # create zones list
+            for index in zones:
+                index_str = str(index)
+                if len(index_str) < 2:
+                    index_str = "0" + index_str
+                zones_folder.append("zone"+index_str)
+
+            # shuffle list of zones (=> randomly choose zones)
+            random.shuffle(zones_folder)
+
+            for id_zone, zone_folder in enumerate(zones_folder):
+                zone_path = os.path.join(scene_path, zone_folder)
+                data_filename = _metric + "_" + _choice + generic_output_file_svd
+                data_file_path = os.path.join(zone_path, data_filename)
+
+                # getting number of line and read randomly lines
+                f = open(data_file_path)
+                lines = f.readlines()
+
+                counter = 0
+                # check if user select current scene and zone to be part of training data set
+                for line in lines:
+
+
+                    begin, end = _interval
+
+                    line_data = line.split(';')
+                    metrics = line_data[begin+1:end+1]
+                    metrics = [float(m) for m in metrics]
+
+                    min_value = min(metrics)
+                    max_value = max(metrics)
+
+                    if min_value < min_value_interval:
+                        min_value_interval = min_value
+
+                    if max_value > max_value_interval:
+                        max_value_interval = max_value
+
+                    counter += 1
+
+
+def generate_data_model(_filename, _interval, _choice, _metric, _scenes = scenes_list, _nb_zones = 4, _percent = 1, _norm = False, _sep=':', _index=True):
 
     output_train_filename = _filename + ".train"
     output_test_filename = _filename + ".test"
@@ -81,50 +151,54 @@ def generate_data_model(_filename, _interval, _choice, _metric, _scenes = scenes
     scenes = [s for s in scenes if min_max_filename not in s]
 
     for id_scene, folder_scene in enumerate(scenes):
-        scene_path = os.path.join(path, folder_scene)
 
-        zones_folder = []
-        # create zones list
-        for index in zones:
-            index_str = str(index)
-            if len(index_str) < 2:
-                index_str = "0" + index_str
-            zones_folder.append("zone"+index_str)
+        # only take care of maxwell scenes
+        if folder_scene in scenes_list:
+
+            scene_path = os.path.join(path, folder_scene)
 
-        # shuffle list of zones (=> randomly choose zones)
-        random.shuffle(zones_folder)
+            zones_folder = []
+            # create zones list
+            for index in zones:
+                index_str = str(index)
+                if len(index_str) < 2:
+                    index_str = "0" + index_str
+                zones_folder.append("zone"+index_str)
 
-        for id_zone, zone_folder in enumerate(zones_folder):
-            zone_path = os.path.join(scene_path, zone_folder)
-            data_filename = _metric + "_" + _choice + generic_output_file_svd
-            data_file_path = os.path.join(zone_path, data_filename)
+            # shuffle list of zones (=> randomly choose zones)
+            random.shuffle(zones_folder)
 
-            # getting number of line and read randomly lines
-            f = open(data_file_path)
-            lines = f.readlines()
+            for id_zone, zone_folder in enumerate(zones_folder):
+                zone_path = os.path.join(scene_path, zone_folder)
+                data_filename = _metric + "_" + _choice + generic_output_file_svd
+                data_file_path = os.path.join(zone_path, data_filename)
 
-            num_lines = len(lines)
+                # getting number of line and read randomly lines
+                f = open(data_file_path)
+                lines = f.readlines()
 
-            lines_indexes = np.arange(num_lines)
-            random.shuffle(lines_indexes)
+                num_lines = len(lines)
 
-            path_seuil = os.path.join(zone_path, seuil_expe_filename)
+                lines_indexes = np.arange(num_lines)
+                random.shuffle(lines_indexes)
 
-            counter = 0
-            # check if user select current scene and zone to be part of training data set
-            for index in lines_indexes:
-                line = construct_new_line(path_seuil, _interval, lines[index], _sep, _index)
+                path_seuil = os.path.join(zone_path, seuil_expe_filename)
 
-                percent = counter / num_lines
+                counter = 0
+                # check if user select current scene and zone to be part of training data set
+                for index in lines_indexes:
+                    line = construct_new_line(path_seuil, _interval, lines[index], _norm, _sep, _index)
 
-                if id_zone < _nb_zones and folder_scene in _scenes and percent <= _percent:
-                    train_file.write(line)
-                else:
-                    test_file.write(line)
+                    percent = counter / num_lines
 
-                counter += 1
+                    if id_zone < _nb_zones and folder_scene in _scenes and percent <= _percent:
+                        train_file.write(line)
+                    else:
+                        test_file.write(line)
 
-            f.close()
+                    counter += 1
+
+                f.close()
 
     train_file.close()
     test_file.close()
@@ -132,19 +206,21 @@ def generate_data_model(_filename, _interval, _choice, _metric, _scenes = scenes
 
 def main():
 
+    p_custom = False
+
     if len(sys.argv) <= 1:
         print('Run with default parameters...')
-        print('python generate_data_model_random.py --output xxxx --interval 0,20  --kind svdne --metric lab --scenes "A, B, D" --nb_zones 5 --percent 0.7 --sep : --rowindex 1')
+        print('python generate_data_model_random.py --output xxxx --interval 0,20  --kind svdne --metric lab --scenes "A, B, D" --nb_zones 5 --percent 0.7 --sep : --rowindex 1 --custom min_max_filename')
         sys.exit(2)
     try:
-        opts, args = getopt.getopt(sys.argv[1:], "ho:i:k:s:n:p:r", ["help=", "output=", "interval=", "kind=", "metric=","scenes=", "nb_zones=", "percent=", "sep=", "rowindex="])
+        opts, args = getopt.getopt(sys.argv[1:], "ho:i:k:s:n:p:r:c", ["help=", "output=", "interval=", "kind=", "metric=","scenes=", "nb_zones=", "percent=", "sep=", "rowindex=", "custom="])
     except getopt.GetoptError:
         # print help information and exit:
-        print('python generate_data_model_random.py --output xxxx --interval 0,20  --kind svdne --metric lab --scenes "A, B, D" --nb_zones 5 --percent 0.7 --sep : --rowindex 1')
+        print('python generate_data_model_random.py --output xxxx --interval 0,20  --kind svdne --metric lab --scenes "A, B, D" --nb_zones 5 --percent 0.7 --sep : --rowindex 1 --custom min_max_filename')
         sys.exit(2)
     for o, a in opts:
         if o == "-h":
-            print('python generate_data_model_random.py --output xxxx --interval 0,20  --kind svdne --metric lab --scenes "A, B, D" --nb_zones 5 --percent 0.7 --sep : --rowindex 1')
+            print('python generate_data_model_random.py --output xxxx --interval 0,20  --kind svdne --metric lab --scenes "A, B, D" --nb_zones 5 --percent 0.7 --sep : --rowindex 1 --custom min_max_filename')
             sys.exit()
         elif o in ("-o", "--output"):
             p_filename = a
@@ -167,6 +243,8 @@ def main():
                 p_rowindex = True
             else:
                 p_rowindex = False
+        elif o in ("-c", "--custom"):
+            p_custom = a
         else:
             assert False, "unhandled option"
 
@@ -175,10 +253,25 @@ def main():
 
     for scene_id in p_scenes:
         index = scenes_indexes.index(scene_id.strip())
-        scenes_selected.append(scenes[index])
+        scenes_selected.append(scenes_list[index])
+
+    # find min max value if necessary to renormalize data
+    if p_custom:
+        get_min_max_value_interval(p_filename, p_interval, p_kind, p_metric)
+
+        # write new file to save
+        if not os.path.exists(custom_min_max_folder):
+            os.makedirs(custom_min_max_folder)
+
+        min_max_folder_path = os.path.join(os.path.dirname(__file__), custom_min_max_folder)
+        min_max_filename_path = os.path.join(min_max_folder_path, p_custom)
+
+        with open(min_max_filename_path, 'w') as f:
+            f.write(str(min_value_interval) + '\n')
+            f.write(str(max_value_interval) + '\n')
 
     # create database using img folder (generate first time only)
-    generate_data_model(p_filename, p_interval, p_kind, p_metric, scenes_selected, p_nb_zones, p_percent, p_sep, p_rowindex)
+    generate_data_model(p_filename, p_interval, p_kind, p_metric, scenes_selected, p_nb_zones, p_percent, p_custom, p_sep, p_rowindex)
 
 if __name__== "__main__":
     main()

generate_data_model_random_maxwell.py

@@ -50,6 +50,7 @@ def construct_new_line(path_seuil, interval, line, norm, sep, index):
 
     metrics = [float(m) for m in metrics]
 
+    # TODO : check if it's always necessary to do that (loss of information for svd)
     if norm:
         metrics = processing.normalize_arr_with_range(metrics, min_value_interval, max_value_interval)
 
@@ -70,7 +71,7 @@ def construct_new_line(path_seuil, interval, line, norm, sep, index):
 
     return line
 
-def get_min_max_value_interval(_filename, _interval, _choice, _metric, _scenes = scenes_list, _nb_zones = 4, _percent = 1):
+def get_min_max_value_interval(_filename, _interval, _choice, _metric):
 
     global min_value_interval, max_value_interval
 
@@ -256,7 +257,7 @@ def main():
 
     # find min max value if necessary to renormalize data
     if p_custom:
-        get_min_max_value_interval(p_filename, p_interval, p_kind, p_metric, scenes_selected, p_nb_zones, p_percent)
+        get_min_max_value_interval(p_filename, p_interval, p_kind, p_metric)
 
         # write new file to save
         if not os.path.exists(custom_min_max_folder):

run_maxwell_simulation.sh

@@ -33,17 +33,16 @@ for size in {"4","8","16","26","32","40"}; do
 
                         FILENAME="data/data_maxwell_N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}"
                         MODEL_NAME="${model}_N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}"
-                        CUSTOM_MIN_MAX_FILENAME="N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}_min_max"
 
                         if grep -q "${MODEL_NAME}" "${simulate_models}"; then
                             echo "Run simulation for model ${MODEL_NAME}"
 
                             # by default regenerate model
-                            python generate_data_model_random_maxwell.py --output ${FILENAME} --interval "${start},${end}" --kind ${mode} --metric ${metric} --scenes "${scenes}" --nb_zones "${nb_zones}" --percent 1 --norm 0 --sep ';' --rowindex '0' --custom ${CUSTOM_MIN_MAX_FILENAME}
+                            python generate_data_model_random_maxwell.py --output ${FILENAME} --interval "${start},${end}" --kind ${mode} --metric ${metric} --scenes "${scenes}" --nb_zones "${nb_zones}" --percent 1 --sep ';' --rowindex '0'
 
                             python train_model.py --data ${FILENAME} --output ${MODEL_NAME} --choice ${model}
 
-                            python predict_seuil_expe_maxwell_curve.py --interval "${start},${end}" --model "saved_models/${MODEL_NAME}.joblib" --mode "${mode}" --metric ${metric} --limit_detection '2' --custom ${CUSTOM_MIN_MAX_FILENAME}
+                            python predict_seuil_expe_maxwell_curve.py --interval "${start},${end}" --model "saved_models/${MODEL_NAME}.joblib" --mode "${mode}" --metric ${metric} --limit_detection '2'
 
                             python save_model_result_in_md_maxwell.py --interval "${start},${end}" --model "saved_models/${MODEL_NAME}.joblib" --mode "${mode}" --metric ${metric}
 

run_maxwell_simulation_custom.sh

@@ -0,0 +1,63 @@
+#! bin/bash
+
+# file which contains model names we want to use for simulation
+simulate_models="simulate_models.csv"
+
+# selection of four scenes (only maxwell)
+scenes="A, D, G, H"
+VECTOR_SIZE=200
+
+for size in {"4","8","16","26","32","40"}; do
+    for metric in {"lab","mscn","mscn_revisited","low_bits_2","low_bits_3","low_bits_4","low_bits_5","low_bits_6","low_bits_4_shifted_2"}; do
+
+        half=$(($size/2))
+        start=-$half
+
+        for counter in {0..4}; do
+             end=$(($start+$size))
+
+             if [ "$end" -gt "$VECTOR_SIZE" ]; then
+                 start=$(($VECTOR_SIZE-$size))
+                 end=$(($VECTOR_SIZE))
+             fi
+
+             if [ "$start" -lt "0" ]; then
+                 start=$((0))
+                 end=$(($size))
+             fi
+
+             for nb_zones in {4,6,8,10,12,14}; do
+
+                 for mode in {"svd","svdn","svdne"}; do
+                     for model in {"svm_model","ensemble_model","ensemble_model_v2"}; do
+
+                        FILENAME="data/data_maxwell_N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}"
+                        MODEL_NAME="${model}_N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}"
+                        CUSTOM_MIN_MAX_FILENAME="N${size}_B${start}_E${end}_nb_zones_${nb_zones}_${metric}_${mode}_min_max"
+
+                        if grep -q "${MODEL_NAME}" "${simulate_models}"; then
+                            echo "Run simulation for model ${MODEL_NAME}"
+
+                            # by default regenerate model
+                            python generate_data_model_random_maxwell.py --output ${FILENAME} --interval "${start},${end}" --kind ${mode} --metric ${metric} --scenes "${scenes}" --nb_zones "${nb_zones}" --percent 1 --norm 0 --sep ';' --rowindex '0' --custom ${CUSTOM_MIN_MAX_FILENAME}
+
+                            python train_model.py --data ${FILENAME} --output ${MODEL_NAME} --choice ${model}
+
+                            python predict_seuil_expe_maxwell_curve.py --interval "${start},${end}" --model "saved_models/${MODEL_NAME}.joblib" --mode "${mode}" --metric ${metric} --limit_detection '2' --custom ${CUSTOM_MIN_MAX_FILENAME}
+
+                            python save_model_result_in_md_maxwell.py --interval "${start},${end}" --model "saved_models/${MODEL_NAME}.joblib" --mode "${mode}" --metric ${metric}
+
+                        fi
+                    done
+                done
+            done
+
+            if [ "$counter" -eq "0" ]; then
+                start=$(($start+50-$half))
+            else
+                start=$(($start+50))
+            fi
+
+        done
+    done
+done