more or less done

Author: JEENB

__pycache__/create_report.cpython-39.pyc

@@ -2,34 +2,27 @@
 from datetime import datetime
 
 
-width = 210
-height = 297
-degree = 2
-split = 20
-points = 100
-training_points = 80
-testing_points = 20
 
-dataset = "dataste.csv"
 
 
-file_name = "report.pdf"
-
 pdf = FPDF()
 
-def section(string):
+def section(string, pdf=pdf):
 	pdf.set_font('Courier','B', 14)  
 	pdf.cell(0,7,string, ln = 2)
 
-def line(string):
+def line(string, pdf= pdf):
 	pdf.set_font('Courier', '', 11)  
 	pdf.cell(0,5,string, ln = 2)
 
-def multi_line(string):
+def multi_line(string, pdf=pdf):
 	pdf.set_font('Courier', '', 11) 
 	pdf.multi_cell(0,5, string)
 
-def create_report():
+def c_report(tot, maxi, mini, mean, medi, sd, training_points, testing_points, degree, split, user_dir):
+	file_name = "report.pdf"
+	width = 210
+	height = 297
 	pdf.set_margins(15,15)
 	pdf.set_title('Regression Report')
 	pdf.set_font('Helvetica', '', 14)  
@@ -47,39 +40,39 @@ def create_report():
 
 	line("")
 	section("User Defined Parameters")
-	line(f"Dataset: {dataset}")
+	line(f"Dataset: received.txt")
 	line(f"Polynomial Degree = {degree}")
 	line(f"Train-test-split = {split}%")
 	line("")
 
 	section("Dataset Exploration")
-	line(f"Total Points = {points}")
+	line(f"Total Points = {tot}")
 	line(f"Training Points = {training_points}")
 	line(f"Testing Points = {testing_points}")
-	line(f"Max = {testing_points}")
-	line(f"Min = {testing_points}")
-	line(f"Mean = {testing_points}")
-	line(f"Median = {testing_points}")
-	line(f"Standard Deviation = {testing_points}")
+	line(f"Max = {maxi}")
+	line(f"Min = {mini}")
+	line(f"Mean = {mean}")
+	line(f"Median = {medi}")
+	line(f"Standard Deviation = {sd}")
 	line("")
 
 	section("Results")
 
 	section("1. Polynomial Fitting")
-	pdf.image("./server_data/fitting.png",50,140,w=120, h = 72)
+	pdf.image(f"{user_dir}/fitting.png",50,140,w=120, h = 72)
 	pdf.ln(84)
 	multi_line("The above figure represents the regression line being fitted to the training instances. If the regression line passes through all the points then the polynomial degree chosen overfits the data. Similarly, if the line does not touch even a single point, you might be underfitting the training instances.")
 
 	pdf.add_page()
 	section("2. Actual vs Predicted")
-	pdf.image("./server_data/actual_pred.png",50,20,w=120, h = 72)
+	pdf.image(f"{user_dir}/actual_pred.png",50,20,w=120, h = 72)
 	pdf.ln(84)
 	multi_line("The above scatter plot represents the spread of predicted and actual scores. Assuming out model perfectly fits the data we can expect the points spread across the y = x line.")
 	line("")
 
 
 	section("3. Residual vs Predicted")
-	pdf.image("./server_data/actual_pred.png",50,140,w=120, h = 72)
+	pdf.image(f"{user_dir}/actual_pred.png",50,140,w=120, h = 72)
 	pdf.ln(84)
 	line("Residual = h(x) - f(x)")
 	line("where,")
@@ -90,13 +83,13 @@ def create_report():
 
 	pdf.add_page()
 	section("4. Mean Squared Error")
-	pdf.image("./server_data/compare_error.png",50,20,w=120, h = 72)
+	pdf.image(f"{user_dir}/compare_error.png",50,20,w=120, h = 72)
 	pdf.ln(80)
 	multi_line("The mean squared error is calculated as the sum of differences in actual and predicted result squared. The lower the MSE the better the model performs.")
 	line("")
 
 	section("4. Normal Q-Q Plots")
-	pdf.image("./server_data/normalqq.png",50,125,w=120, h = 72)
+	pdf.image(f"{user_dir}/normalqq.png",50,125,w=120, h = 72)
 	pdf.ln(75)
 	line("")
 	multi_line("The Q-Q plot, or quantile-quantile plot, is a graphical tool to help us assess if a set of data plausibly came from some theoretical distribution such as a Normal or exponential. For example, if we run a statistical analysis that assumes our dependent variable is Normally distributed, we can use a Normal Q-Q plot to check that assumption. It's just a visual check, not an air-tight proof, so it is somewhat subjective. But it allows us to see at-a-glance if our assumption is plausible, and if not, how the assumption is violated and what data points contribute to the violation.")
@@ -106,7 +99,6 @@ def create_report():
 	pdf.add_page()
 	pdf.image("./report/2.png",0,0,width)
 
-	pdf.output("./server_data/report.pdf", 'F')
-
+	pdf.output(f"{user_dir}/report.pdf", 'F')
+	return 0
 
-create_report()

__pycache__/models.cpython-39.pyc

@@ -14,7 +14,7 @@
 import statsmodels.api as sm
 
 
-def reg_training_model(df, degree = 1, split_ratio = 0.2, email ="dummy"):
+def reg_training_model(df, user_dir, degree = 1, split_ratio = 0.2):
 	'''
 	function: poly_reg (Gives the polynomial regression for a set of data)
 		Using PolymnomialFeatures and LinearRegression functions, fits a polynomial of degree n.  
@@ -67,7 +67,7 @@ def reg_training_model(df, degree = 1, split_ratio = 0.2, email ="dummy"):
 	plt.plot(df.x_test, df.y_test_pred, label = "Polynomial degree = {}".format(degree), color='r')
 	plt.legend(loc='upper left')	
 	plt.title("Polynomial Fitting")
-	plt.savefig("server_data/fitting.png")
+	plt.savefig(f"{user_dir}/fitting.png")
 	plt.show()
 
 
@@ -90,7 +90,7 @@ def reg_training_model(df, degree = 1, split_ratio = 0.2, email ="dummy"):
 	plt.ylabel("Predicted Results")
 	plt.legend(loc='upper left')	
 	plt.title("Actual VS Predicted")
-	plt.savefig("server_data/actual_pred.png")
+	plt.savefig(f"{user_dir}/actual_pred.png")
 
 
 
@@ -102,7 +102,7 @@ def reg_training_model(df, degree = 1, split_ratio = 0.2, email ="dummy"):
 	plt.ylabel("Dataset")
 	plt.ylabel("Mean Square Error")
 	plt.title("Comparing Errors")
-	plt.savefig("server_data/compare_error.png")
+	plt.savefig(f"{user_dir}/compare_error.png")
 
 
 
@@ -119,7 +119,7 @@ def reg_training_model(df, degree = 1, split_ratio = 0.2, email ="dummy"):
 	plt.ylabel("Residual")
 	plt.legend(loc='upper left')	
 	plt.title("Residual VS Predicted")
-	plt.savefig("server_data/residual_pred.png")
+	plt.savefig(f"{user_dir}/residual_pred.png")
 
 
 
@@ -135,6 +135,6 @@ def reg_training_model(df, degree = 1, split_ratio = 0.2, email ="dummy"):
 	sm.qqplot(residual_test, line='45',  ax = ax2)
 	ax2.set_title("Test")
 	ax2.set_ylabel("Standard Residual")
-	plt.savefig("server_data/residual_pred.png")
+	plt.savefig(f"{user_dir}/residual_pred.png")
 	return 0
 

__pycache__/utils.cpython-39.pyc

@@ -4,19 +4,38 @@
 import time
 from models import *
 import pandas as pd
+from utils import *
+from create_report import *
 
 PORT = 2223
 SERVER = socket.gethostname()
 server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
 server.bind((SERVER, PORT))
+HEADER = 2048
+
+server_dir = "./server_data/"
 
 while True:
     server.listen(5)
     print(f"[LISTENING] Server is listening on {SERVER}")
     conn, addr = server.accept()
     print("Connection established with " + str(addr[0]) + ", " + str(addr[1]))
 
-    file_name = 'received.csv'
+    # email = server.recv(HEADER).decode()
+    # initial = email.split('@')[0]
+    # password = server.recv(HEADER).decode()
+
+    initial = "jen"
+     
+    user_dir = os.path.join(server_dir, initial)
+    if os.path.isdir(user_dir):
+        pass
+    else:
+        os.mkdir(user_dir)
+
+    
+
+    file_name = f'./server_data/{initial}/received.csv'
     file_size = conn.recv(100).decode()
     print(file_size)
     # Opening and reading file.
@@ -50,8 +69,12 @@
 
 
     df = pd.read_csv(file_name)
-    reg_training_model(df, degree = int(degree), split_ratio = int(training_ratio)/100 )
-    
+    training_points = int(len(df)*int(training_ratio)/100)
+    testing_points = len(df) - training_points
+    reg_training_model(df, degree = int(degree), split_ratio = int(training_ratio)/100, user_dir = user_dir)
+
+    tot, maxi, mini, mean, medi, sd = stats_summary(df)
+    c_report(tot, maxi, mini, mean, medi, sd, training_points, testing_points, degree, split = training_ratio, user_dir = user_dir)
 
     # Closing the socket.
     conn.close()