paths work

clustering_precomputed_dbscan.py

@@ -5,9 +5,9 @@ import csv
 from math import sqrt
 from sklearn.cluster import DBSCAN
 
-def get_average_xy(list_input):
-    csv_name = "/home/centurio/Projects/engineering_drawings_extraction/temporary/ist_to_csv_with_corner_points.csv"
-    resultFile = open(csv_name, 'w')
+def get_average_xy(list_input, path):
+    csv_name = path+"/temporary/list_to_csv_with_corner_points.csv"
+    resultFile = open(csv_name, 'w+')
     wr = csv.writer(resultFile, delimiter=";")
     wr.writerow(["element", "xmin","ymin","xmax","ymax", "ausrichtung","point_xmi_ymi","point_xma_ymi","point_xmi_yma","point_xma_yma"])
     result_df = pandas.DataFrame(columns=["point_xmi_ymi","point_xma_ymi","point_xmi_yma","point_xma_yma","ausrichtung"])
@@ -112,28 +112,28 @@ def dist(rectangle1, rectangle2):
             #print(rectangle1)
     return distance
 
-def clustering(dm,eps):
+def clustering(dm,eps,path):
     db = DBSCAN(eps=eps, min_samples=1, metric="precomputed").fit(dm)                                                                                        ##3.93 until now, bei 5 shon mehr erkannt, 7 noch mehr erkannt aber auch schon zu viel; GV12 ist 4.5 gut für LH zu wenig
     labels = db.labels_
     n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
 
     print('Estimated number of clusters: %d' % n_clusters_)
-    data_df = pandas.read_csv("/home/centurio/Projects/engineering_drawings_extraction/temporary/list_to_csv_with_corner_points.csv", sep=";")
+    data_df = pandas.read_csv(path +"/temporary/list_to_csv_with_corner_points.csv", sep=";")
     data_df["cluster"] = labels
-    data_df.groupby(['cluster', 'ausrichtung'])['element'].apply(','.join).reset_index().to_csv("//home/centurio/Projects/engineering_drawings_extraction/temporary/values_clusteredfrom_precomputed_dbscan.csv",sep=";", header=False, index=False)
+    data_df.groupby(['cluster', 'ausrichtung'])['element'].apply(','.join).reset_index().to_csv(path+"/temporary/values_clusteredfrom_precomputed_dbscan.csv",sep=";", header=False, index=False)
     return data_df
 
-def cluster_and_preprocess(result,eps):
-    result = get_average_xy(result) #input: array of arrays, output: either csv file or array of arrays
+def cluster_and_preprocess(result,eps,path):
+    result = get_average_xy(result, path) #input: array of arrays, output: either csv file or array of arrays
 
     #data = pandas.read_csv("/home/bscheibel/PycharmProjects/dxf_reader/temporary/list_to_csv_with_corner_points.csv", sep=";")
     #data = data[["point_xmi_ymi","point_xma_ymi","point_xmi_yma","point_xma_yma","ausrichtung"]]
-    result.to_csv("/home/centurio/Projects/engineering_drawings_extraction/temporary/blub.csv", sep=";", index=False, header=None)
-    with open('/home/centurio/Projects/engineering_drawings_extraction/temporary/blub.csv') as csvfile:
+    result.to_csv(path+"/temporary/blub.csv", sep=";", index=False, header=None)
+    with open(path+"/temporary/blub.csv") as csvfile:
         readCSV = csv.reader(csvfile, delimiter=';')
         result = list(readCSV)
 
     dm = np.asarray([[dist(p1, p2) for p2 in result] for p1 in result])
-    clustering_result = clustering(dm,float(eps))
+    clustering_result = clustering(dm,float(eps), path)
     return clustering_result
 

main.py

@@ -14,7 +14,9 @@ def write_redis(uuid, result, db_params):
 
 
 def main(uuid, filepath, db, eps):
-    filename = order_bounding_boxes_in_each_block.pdf_to_html(uuid, filepath)
+    #path_centurio = "/home/centurio/Projects/engineering_drawings_extraction"
+    path = "/home/bscheibel/PycharmProjects/dxf_reader"
+    filename = order_bounding_boxes_in_each_block.pdf_to_html(uuid, filepath, path)
     #print(filename)
     result, number_blocks, number_words= order_bounding_boxes_in_each_block.get_bound_box(filename)  ##get coordinates+text out of html file into array of arrays
     if eps == '0':
@@ -25,8 +27,8 @@ def main(uuid, filepath, db, eps):
     #print(eps)
     isos, general_tol = order_bounding_boxes_in_each_block.extract_isos(result)
     print(general_tol)
-    res = clustering_precomputed_dbscan.cluster_and_preprocess(result,eps)
-    clean_arrays = read_from_clustered_merged.read("/home/centurio/Projects/engineering_drawings_extraction/temporary/values_clusteredfrom_precomputed_dbscan.csv")
+    res = clustering_precomputed_dbscan.cluster_and_preprocess(result,eps, path)
+    clean_arrays = read_from_clustered_merged.read(path+"/temporary/values_clusteredfrom_precomputed_dbscan.csv")
     tables = order_bounding_boxes_in_each_block.get_tables(clean_arrays)
     pretty = regex_clean_new.print_clean(clean_arrays)
     res, details_dict = organize_drawing_according_to_details_new.main_function(pretty, tables)
@@ -44,11 +46,10 @@ def main(uuid, filepath, db, eps):
     #print(redis.Redis('localhost').get(uuid+"dims"))
     #print(result)
 
-"""if __name__ == "__main__":
+"""#if __name__ == "__main__":
     uuid = sys.argv[1]
     filename = sys.argv[2]
     db = sys.argv[3]
     eps = sys.argv[4]
-    main(uuid,filename, db, eps)
-"""
+    main(uuid,filename, db, eps)"""
 main("33333", "/home/bscheibel/PycharmProjects/dxf_reader/drawings/5152166_Rev04.pdf", "localhost",3)

order_bounding_boxes_in_each_block.py

@@ -54,8 +54,8 @@ def get_bound_box(file):
 
     return new_all_elements, number_blocks, number_words
 
-def pdf_to_html(uuid,filepath):
-    filename = "temporary/" +str(uuid)+"out.html" #to app/temporary later
+def pdf_to_html(uuid,filepath, path):
+    filename = path +"/temporary/" +str(uuid)+"out.html" #to app/temporary later
     subprocess.call(['pdftotext', '-bbox-layout',
                      filepath, filename])
     return filename