hovedguy · November 3, 2018 12:16
diff --git a/B_15_inpParserForNodes_optimized.py b/B_15_inpParserForNodes_optimized.py
 import pandas as pd
 import time

 start_time = time.time()

 full_path = r"C:\Temp\Example_3\Job-1.inp" # inp full file path

 with open(full_path, "r") as f:
    f_data = f.read()
    file_list_ = f_data.split("\n") # creates list of all lines
    # OP: ['*Heading', '** Job name: Job-1 Model name: Model-1', ....]

 def nodeParser(file_list):
    ''' creates pandas data-frame in the form of - 
    
    part_id, node_id, node_x, node_y, node_z as
    int    , int    , float , float , float'''
    
    node_start = []
    node_end = []
    node_flag = False

    for x in range(len(file_list)):
        if "*Part," in file_list[x - 2] and "*Node" in file_list[x - 1]:
            node_start.append(x)
            node_flag = True

        if node_flag and "*" in file_list[x]:
            node_end.append(x - 1)
            node_flag = False

    node_band = list(zip(node_start, node_end))  # creates a list of tuples containing start and end of line nums containing node def
    # OP: [(9, 104), (192, 202)]

    node_band_dict = {}  # creates a dict of part id vs tuple containing same info node_band
    # OP: {1: (9, 104), 2: (192, 202)}
    for x in range(len(node_band)):
        node_band_dict[x + 1] = node_band[x]

    d_cont = []  # node data content as list, all elements are stored as string
    # OP: [['*Heading'], ['** Job name: Job-1 Model name: Model-1'], ...]
    for i in range(len(file_list)):
        b = file_list[i].split(",")
        final = list(b[x].strip() for x in range(len(b)))
        d_cont.append(final)

    df = pd.DataFrame(columns = ["part_id", "node_id", "node_x", "node_y", "node_z"])

    for key, val in node_band_dict.items():
        df_local = pd.DataFrame(columns = ["node_id", "node_x", "node_y", "node_z"])
        for line in range(len(d_cont[val[0]:val[1]])):
            df_local.loc[line] = d_cont[val[0]:val[1]][line]
        df_local["part_id"] = list(key for _ in range(len(df_local.node_id)))
        column_list = df_local.columns.tolist()
        df_local = df_local[ [column_list[-1]] + column_list[:-1] ]
        df = df.append(df_local, ignore_index=True)

    # to change data type
    coords = df.columns.drop("part_id", "node_id")
    df[coords] = df[coords].apply(pd.to_numeric, errors='coerce')  # creates float
    df.node_id = df.node_id.astype(int)  # creates integer
    df.part_id = df.part_id.astype(int)

    return df

 def main():
    node_df = nodeParser(file_list_)
    print(node_df.head())

    delta_time = time.time() - start_time
    print(f"JOB'S COMPLETED, TIME TAKEN: {delta_time} sec")

 main()
	import pandas as pd
	import time

	start_time = time.time()

	full_path = r"C:\Temp\Example_3\Job-1.inp" # inp full file path

	with open(full_path, "r") as f:
	f_data = f.read()
	file_list_ = f_data.split("\n") # creates list of all lines
	# OP: ['Heading', '* Job name: Job-1 Model name: Model-1', ....]

	def nodeParser(file_list):
	''' creates pandas data-frame in the form of -

	part_id, node_id, node_x, node_y, node_z as
	int , int , float , float , float'''

	node_start = []
	node_end = []
	node_flag = False

	for x in range(len(file_list)):
	if "Part," in file_list[x - 2] and "Node" in file_list[x - 1]:
	node_start.append(x)
	node_flag = True

	if node_flag and "*" in file_list[x]:
	node_end.append(x - 1)
	node_flag = False

	node_band = list(zip(node_start, node_end)) # creates a list of tuples containing start and end of line nums containing node def
	# OP: [(9, 104), (192, 202)]

	node_band_dict = {} # creates a dict of part id vs tuple containing same info node_band
	# OP: {1: (9, 104), 2: (192, 202)}
	for x in range(len(node_band)):
	node_band_dict[x + 1] = node_band[x]

	d_cont = [] # node data content as list, all elements are stored as string
	# OP: [['Heading'], ['* Job name: Job-1 Model name: Model-1'], ...]
	for i in range(len(file_list)):
	b = file_list[i].split(",")
	final = list(b[x].strip() for x in range(len(b)))
	d_cont.append(final)

	df = pd.DataFrame(columns = ["part_id", "node_id", "node_x", "node_y", "node_z"])

	for key, val in node_band_dict.items():
	df_local = pd.DataFrame(columns = ["node_id", "node_x", "node_y", "node_z"])
	for line in range(len(d_cont[val[0]:val[1]])):
	df_local.loc[line] = d_cont[val[0]:val[1]][line]
	df_local["part_id"] = list(key for _ in range(len(df_local.node_id)))
	column_list = df_local.columns.tolist()
	df_local = df_local[ [column_list[-1]] + column_list[:-1] ]
	df = df.append(df_local, ignore_index=True)

	# to change data type
	coords = df.columns.drop("part_id", "node_id")
	df[coords] = df[coords].apply(pd.to_numeric, errors='coerce') # creates float
	df.node_id = df.node_id.astype(int) # creates integer
	df.part_id = df.part_id.astype(int)

	return df

	def main():
	node_df = nodeParser(file_list_)
	print(node_df.head())

	delta_time = time.time() - start_time
	print(f"JOB'S COMPLETED, TIME TAKEN: {delta_time} sec")

	main()