Initial commit

gitrepo @ e484aa53

+Subproject commit e484aa5316fb4bb36fc2cfef5f7fb936a779c89a

nisum_json.py

+import os
+import json
+import git
+import csv
+import pandas as pd
+import numpy as np
+
+#Ask for File Location Input
+
+
+while True:
+	try:
+		mychoice = int(input("Please enter select a number choice. Where is the JSON file located: \n 1) Local. 2) GitRepo. : "))
+	except ValueError:
+		print('Your input is invalid. Please enter a number.')
+
+	if mychoice == 1:
+		localpath = input("Please enter the absolute file path of directory where JSON file is located. Do not include filename.: ")
+		filename = input("Please enter the filename including file extension: ")
+		filepath = (os.path.join(localpath, filename))
+		print("File path: "+filepath)
+		try:
+			print("Opening File.")
+			myfile = open(filepath, 'r')
+			print("File Opened!")
+			print("Reading File.")
+			try:
+				filedata = myfile.read()
+				print("File Read!")
+				print("Checking if data is valid JSON.")
+				try:
+					json.loads(filedata)
+					print("Data is valid JSON!")
+					print(filedata)
+					print("Converting JSON into CSV.")
+					with open(filepath) as json_file:
+						json_data = json.load(json_file)
+					csvfilename = input("Please enter a name for the CSV file:")
+					fullcsvfilename = csvfilename+".csv"
+					# now we will open a file for writing
+					data_file = open(fullcsvfilename, 'w')
+					# create the csv writer object
+					csv_writer = csv.writer(data_file)
+					# Counter variable used for writing
+					# headers to the CSV file
+					count = 0
+					for emp in json_data:
+						if count == 0:
+							# Writing headers of CSV file
+							header = emp.keys()
+							csv_writer.writerow(header)
+							count += 1
+						# Writing data of CSV file
+						csv_writer.writerow(emp.values())
+					data_file.close()
+					# read CSV file
+					# numcolumns = pd.read_csv(file, nrows=1).select_dtypes("number").columns
+					
+
+					results = pd.read_csv(fullcsvfilename)
+					# numeric_data = results.select_dtypes(include=[np.number])
+					# string_data = results.select_dtypes(exclude=[np.number])
+
+					# count no. of lines
+					print("Number of lines present:",len(results))
+					# find the maximum of each numeric column
+
+					# maxValues = numeric_data.max()
+					# print(maxValues)
+
+					
+
+					#find the maximum of each string colums
+					def output_analysis(file_dir):
+						df = pd.read_csv(file_dir)
+						header = list(df.columns.values)
+						for i in range(0, len(header) - 1):
+							string_length = df[header[i]].astype(str).map(len)
+							result = df.loc[string_length.argmax(), header[i]]
+							if not str(result).replace('.', '', 1).isdigit():
+								print("{} : {}".format(header[i], result))
+							else:
+								print("{} : {}".format(header[i], df[header[i]].max()))
+
+					print(output_analysis(fullcsvfilename))
+
+					
+
+					
+
+					
+
+
+				except IOError:
+					print("The data in "+filename+" is not valid JSON.")
+			except IOError:
+					print("Error: "+filename+" cannot be read!")
+		except IOError:
+			print("Error: Please enter the correct file path and file name!")
+			
+		break
+	elif mychoice == 2:
+		giturl = input("Please enter the url of the Git Repo: ")
+		filename = input("Please enter the name of the json file including file extension: ")
+		repopath = input("Please enter the absolute file path for directory where you want to clone the Git Repo: ")
+		gitfilepath = (os.path.join(repopath, filename))
+		print("Repository Path: "+repopath)
+		try:
+			print("Cloning Repo.")
+			repo = git.Repo.clone_from(giturl, repopath)
+			print("Repo Cloned!")
+			try:
+				print("Opening File.")
+				myfile = open(gitfilepath, 'r')
+				print("File Opened!")
+				print("Reading File.")
+				try:
+					filedata = myfile.read()
+					print("File Read!")
+					print("Checking if data is valid JSON.")
+					try:
+						json.loads(filedata)
+						print("Data is valid JSON!")
+						print(filedata)
+						print("Converting JSON into CSV.")
+						with open(gitfilepath) as json_file:
+							json_data = json.load(json_file)
+						csvfilename = input("Please enter a name for the CSV file including :")
+						fullcsvfilename = csvfilename+".csv"
+						# now we will open a file for writing
+						data_file = open(fullcsvfilename, 'w')
+						# create the csv writer object
+						csv_writer = csv.writer(data_file)
+						# Counter variable used for writing
+						# headers to the CSV file
+						count = 0
+						for emp in json_data:
+							if count == 0:
+								# Writing headers of CSV file
+								header = emp.keys()
+								csv_writer.writerow(header)
+								count += 1
+							# Writing data of CSV file
+							csv_writer.writerow(emp.values())
+						data_file.close()
+						# read CSV file
+						# numcolumns = pd.read_csv(file, nrows=1).select_dtypes("number").columns
+						results = pd.read_csv(fullcsvfilename)
+						# count no. of lines
+						print("Number of lines present:",len(results))
+						# find the maximum of each column
+						def output_analysis(file_dir):
+							df = pd.read_csv(file_dir)
+							header = list(df.columns.values)
+							for i in range(0, len(header) - 1):
+								string_length = df[header[i]].astype(str).map(len)
+								result = df.loc[string_length.argmax(), header[i]]
+								if not str(result).replace('.', '', 1).isdigit():
+									print("{} : {}".format(header[i], result))
+								else:
+									print("{} : {}".format(header[i], df[header[i]].max()))
+
+						print(output_analysis(fullcsvfilename))
+
+					except IOError:
+						print("Error: The data in "+filename+" is not valid JSON.")
+				except IOError:
+					print("Error: "+filename+" cannot be read!")
+			except IOError:
+				print("Error: Please enter the correct file path and file name!")
+		except:
+			print("Error: URL Incorrect, Repository Does Not Exist, or Repo Cannot Be Accessed!")
+		
+		break
+	else:
+		print("Invalid Choice")
+
+
+
+		
+	
+	
+	
+	
+	
+
+
+    # elif choice != ('A', 'B')
+    #     print("Incorrect Input. Please select 'A' or 'B'.")
+    #     continue
+