def main(): args = (sys.argv) inputFile= str(args[1]) outputFile= str(args[2]) depth = int(args[3]) try: root = fun.getFileContent(inputFile) child_branch= fun.MiniMax(root,depth,True) children = fun.GenerateMovesOpening(root) fun.writeToFile(outputFile,children[child_branch]) except Exception as e: print("An Error occured :",e)
def main(): thread_in = fns.inverted_thread_class() thread_seq = fns.sequential_thread_class() thread_in.start() thread_seq.start() thread_in.join() thread_seq.join() fns.addToUids() fns.writeToFile() thread_find_in = fns.find_name_in_thread_class() thread_find_seq = fns.find_name_seq_thread_class() thread_find_in.start() thread_find_seq.start() thread_find_in.join() thread_find_seq.join() fns.writeNames() fns.makeMarkdown()
for row in innerbody: if row[0][0] == "": continue doc2list[row[0][0]] = row[0] doc2list[row[2][0]] = row[2] doc2list[row[4][0]] = row[4] count += 1 notpresent = list() present = list() for record in doc2list.values(): if doc1list.get(record[0]): for row in doc1list: del row[3] del row[4] del row[5] present.append(record) else: notpresent.append(record) document1 = Document(docx="D:\\PycharmProjects\\docfilefinder\\MASTERRYANLABELFILE.docx") tables = document1.tables for tab in tables: print("Columns: ", len(tab.columns), "Rows: ", len(tab.rows)) tab = tables[0] writeToFile(notpresent, document1, tab)
def triplify_dataset(change_file, parcel_file, output_folder): startEpoch = time.time() files = [] print('Compute and triplify change detection result') village = parcel_file[-20:-15] triples = [] iFiles = 0 iTriples = 0 lsNameSpaces, lsTriplesTemplate = readTemplate(templateFile) changeFile = rasterio.open(change_file) print("Change data read, CRS (expected 32630):", changeFile.crs) img1 = changeFile.tags()['T1_Product_ID'] img2 = changeFile.tags()['T2_Product_ID'] start_date = changeFile.tags()['T1_Start_Date'] end_date = changeFile.tags()['T2_Start_Date'] parcelFile = gpd.read_file(parcel_file) if '.shp' in parcel_file: project = partial( pyproj.transform, pyproj.Proj(init='epsg:4326'), pyproj.Proj(init=changeFile.crs)) for index, row in parcelFile.iterrows(): clear_output() print(str(index) + '/' + str(len(parcelFile))) feat = {} feat['id'] = row['id'] feat['parcel'] = row['id'] try: geom = transform(project, row['geometry']) parcelChange, changeTransform = mask(changeFile, [geom], crop=True, indexes=1, nodata=-1) except ValueError as err: print(err) continue total = parcelChange[parcelChange>=0].size if total <= 0: try: geom = transform(project, row['geometry']) parcelChange, changeTransform = mask(changeFile, [geom], crop=True, all_touched=True, indexes=1, nodata=-1) except ValueError as err: print(err) continue if total > 0: feat['nop'] = round(parcelChange[(parcelChange < 0.1) & (parcelChange >= 0)].size*100/total,2) feat['lowp'] = round(parcelChange[(parcelChange >= 0.1) & (parcelChange < 0.4)].size*100/total,2) feat['midp'] = round(parcelChange[(parcelChange >= 0.4) & (parcelChange < 0.7)].size*100/total,2) feat['highp'] = round(parcelChange[(parcelChange >= 0.7)].size*100/total,2) feat['id'] = "PC" + str(feat['id']) + "_" + start_date + "_" + end_date feat['id'] = str(feat['id']).replace('-','_') feat['image1'] = img1 feat['image2'] = img2 uriDummy = URIBase + 'Change/' + str(feat['id'])+">" triplesRow = triplify(feat, lsTriplesTemplate, uriDummy, str(feat['id']), str(feat['parcel'])) triples = triples + triplesRow else: print("no data on this parcel") file = output_folder + 'change.ttl' files.append(file) writeToFile(lsNameSpaces, triples, output_folder) clear_output() print('Number of triples', iTriples) print('Number of parcel', len(parcelFile)) endEpoch = time.time() elapsedTime = endEpoch - startEpoch if elapsedTime < 60: print('Elapsed time : ', elapsedTime, ' seconds') else: print('Elapsed time : ', math.floor(elapsedTime / 60), ' minutes and ', elapsedTime % 60, ' seconds') return files
def triplify_dataset(file, parcel_file, product_id, output_folder='./rdf'): startEpoch = time.time() files = [] triples = [] iFiles = 0 iTriples = 0 village = parcel_file[-20:-15] lsNameSpaces, lsTriplesTemplate = readTemplate(templateFile) ndvi_file = rasterio.open(file) print("ndvi_file data read, CRS (expected 32630):", ndvi_file.crs) parcelFile = gpd.read_file(parcel_file) if '/' in file: image_date = file[file.rfind('/') + 1:-7] else: image_date = file[0:-7] project = partial(pyproj.transform, pyproj.Proj(init='epsg:4326'), pyproj.Proj(init=ndvi_file.crs)) for index, row in parcelFile.iterrows(): clear_output() print(str(index) + '/' + str(len(parcelFile))) feat = {} feat['id'] = str(row['id']) feat['parcel'] = str(row['id']) feat['area_type'] = str(row['area_type']) feat['geojson'] = shape(row['geometry']).wkt try: geom = transform(project, row['geometry']) ndviParcel, ndviTransform = mask(ndvi_file, [geom], crop=True, all_touched=True, indexes=1) except ValueError as err: print(err) continue ndvi = np.float16(ndviParcel) total = ndvi[ndvi >= 0.2].size if total <= 0: try: geom = transform(project, row['geometry']) ndviParcel, ndviTransform = mask(ndvi_file, [geom], crop=True, indexes=1) except ValueError as err: print(err) continue ndvi = np.float16(ndviParcel) total = ndvi[ndvi >= 0.2].size if total > 0: feat['lowp'] = round( ndvi[(ndvi >= 0.2) & (ndvi < 0.5)].size * 100 / total, 2) feat['midp'] = round( ndvi[(ndvi >= 0.5) & (ndvi < 0.7)].size * 100 / total, 2) feat['highp'] = round(ndvi[(ndvi >= 0.7)].size * 100 / total, 2) feat['id'] = "PN" + feat['id'] + "_" + image_date feat['id'] = feat['id'].replace('-', '_') feat['image'] = product_id uriDummy = URIBase + 'NDVI/' + feat['id'] + ">" triplesRow = triplify(feat, lsTriplesTemplate, uriDummy, feat['id'], feat['parcel']) triples = triples + triplesRow if len(triples) > maxRecordsPerFile: file = output_folder files.append(file) writeToFile(lsNameSpaces, triples, file) iFiles = iFiles + 1 iTriples = iTriples + len(triples) triples = [] else: print("Too small!") file = output_folder + 'ndvi.ttl' writeToFile(lsNameSpaces, triples, file) files.append(file) clear_output() print('Number of parcel', len(parcelFile)) print('Number of triples', iTriples) endEpoch = time.time() elapsedTime = endEpoch - startEpoch if elapsedTime < 60: print('Elapsed time : ', elapsedTime, ' seconds') else: print('Elapsed time : ', math.floor(elapsedTime / 60), ' minutes and ', elapsedTime % 60, ' seconds') return files
def triplify_dataset(cesbio_file, parcel_file, output_folder): startEpoch = time.time() print('triplify Cadastral parcel and its land-cover') village = parcel_file[-20:-15] triples = [] files = [] iFiles = 0 iTriples = 0 lsNameSpaces, lsTriplesTemplate = readTemplate(templateFile) CesbioFile = rasterio.open(cesbio_file) print("Land cover (expected 4326):", CesbioFile.crs) parcelFile = gpd.read_file(parcel_file) print(CesbioFile.crs) if '.shp' in parcel_file: project = partial(pyproj.transform, pyproj.Proj(init='epsg:4326'), pyproj.Proj(init='epsg:4326')) for index, row in parcelFile.iterrows(): clear_output() print(str(index) + '/' + str(len(parcelFile))) feat = {} feat['id'] = row['id'] feat['geojson'] = shape(row['geometry']).wkt try: geom = transform(project, row['geometry']) LCParcel, LCTransform = mask(CesbioFile, [geom], crop=True, indexes=1, nodata=0) except ValueError as err: print(err) continue if np.count_nonzero(LCParcel) <= 0: try: geom = transform(project, row['geometry']) LCParcel, LCTransform = mask(CesbioFile, [geom], crop=True, all_touched=True, indexes=1, nodata=0) except ValueError as err: print(err) continue if np.count_nonzero(LCParcel) > 0: counter = Counter(LCParcel.ravel()) dominantLCCode, DominantLCFreq = counter.most_common(2)[0] if dominantLCCode == 0: dominantLCCode, DominantLCFreq = counter.most_common(2)[1] percentage = round( DominantLCFreq * 100 / np.count_nonzero(LCParcel), 0) feat['lc'] = correspond_land_cover(dominantLCCode) URI = URIBase + 'Parcel/' + str(row['id']) + ">" triplesRow = triplify(feat, lsTriplesTemplate, URI, "p" + str(row['id'])) triples = triples + triplesRow else: print("Too small!") file = output_folder + 'land_cover.ttl' files.append(file) writeToFile(lsNameSpaces, triples, file) clear_output() print('Number of triples', iTriples) print('Number of parcel', len(parcelFile)) endEpoch = time.time() elapsedTime = endEpoch - startEpoch if elapsedTime < 60: print('Elapsed time : ', elapsedTime, ' seconds') else: print('Elapsed time : ', math.floor(elapsedTime / 60), ' minutes and ', elapsedTime % 60, ' seconds') return files
def sort_trans(dset, new_file_name, file): f = open(file, 'r') fw = open(new_file_name, 'w') fw_tst = open(new_file_name + 'test', 'w') wp = "" wp_tst = "" total_trans = DSET1_TRANS_CNT bucket_list = [0, 0] line = f.readline() if dset == 2: line = f.readline() total_trans = DSET2_TRANS_CNT prod_sup = {} trans_small = RPERC[1] * total_trans trans_big = RPERC[0] * total_trans while line != "": line = line.strip() trans = line.split(';') trans.sort() if bucket_list[1] < trans_small: if bucket_list[0] >= trans_big: bucket = 1 else: bucket = random.randint(0, 1) else: bucket = 0 if bucket == 0: for item in trans: if not prod_sup.has_key(item): prod_sup[item] = 1 else: prod_sup[item] += 1 sp = ';'.join(trans) wp += sp + '\n' if len(wp) > 5000: fw.write(wp) wp = "" else: for item in trans: if not prod_sup.has_key(item): prod_sup[item] = 0 sp_tst = ';'.join(trans) wp_tst += sp_tst + '\n' if len(wp_tst) > 5000: fw_tst.write(wp_tst) wp_tst = "" bucket_list[bucket] += 1 line = f.readline() if len(wp) > 0: fw.write(wp) if len(wp_tst) > 0: fw_tst.write(wp_tst) fw.close() fw_tst.close() prod_list = prod_sup.keys() prod_list.sort() if dset == 1: writeToFile('DSET1/prod_list.txt', prod_list, []) writeToFile('DSET1/prod_sup.txt', prod_sup, []) else: if new_file_name == 'DSET2/trans_prod_sort.txt': writeToFile('DSET2/prod_list.txt', prod_list, []) writeToFile('DSET2/prod_sup.txt', prod_sup, []) else: writeToFile('DSET2/prod_sup_tst.txt', prod_sup, [])