Project-2(A20541036,A20541032)

Data/Data_generator.py

@@ -0,0 +1,40 @@
+import numpy as np
+import pandas as pd
+
+class SyntheticDataGenerator:
+    def __init__(self, rows, cols, noise_level=0.4, random_seed=20):
+        self.rows = rows
+        self.cols = cols
+        self.noise_level = noise_level
+        self.random_seed = random_seed
+
+    def generate_data(self):
+        np.random.seed(self.random_seed)
+        X = np.random.randn(self.rows, self.cols)
+        coefficients = np.random.randn(self.cols)
+        coefficients[2:5] = 0  # Set some coefficients to 0 for sparsity
+        noise = np.random.randn(self.rows) * self.noise_level
+        y = X @ coefficients + noise
+
+        df = pd.DataFrame(X, columns=[f'feature_{i+1}' for i in range(self.cols)])
+        df['target'] = y
+
+        return df.drop(columns='target').to_numpy(), df['target'].to_numpy()
+
+
+class CustomDataGenerator:
+    def __init__(self, coefficients, num_samples, intercept=0, value_range=(-10, 10), noise_scale=1, random_seed=86413459):
+        self.coefficients = np.array(coefficients)
+        self.num_samples = num_samples
+        self.intercept = intercept
+        self.value_range = value_range
+        self.noise_scale = noise_scale
+        self.random_seed = random_seed
+
+    def generate_linear_data(self):
+        np.random.seed(self.random_seed)
+        rng = np.random
+        X = rng.uniform(low=self.value_range[0], high=self.value_range[1], size=(self.num_samples, len(self.coefficients)))
+        y = X @ self.coefficients + self.intercept
+        noise = rng.normal(loc=0.0, scale=self.noise_scale, size=y.shape)
+        return X, y + noise

Data/small_test.csv

@@ -0,0 +1,51 @@
+x_0,x_1,x_2,y
+-2.421348566501347,6.290215260063935,2.516304163087373,10.240119830146476
+8.13465811997068,-6.975968662410185,-3.2810945459842866,-6.8962940548446845
+-0.4531238994261493,0.05889462611191654,-3.592293253611172,14.10428803155231
+3.979832584128687,-8.129001764124755,9.202914789330517,-43.788867687445624
+-4.354231825431758,2.4724749171156333,8.45972163584499,-12.067617018047834
+8.726620980175113,-9.607722575405269,-5.092837184080405,-8.265643240683891
+-0.29136484802189955,8.224663789274086,-3.8193339707565555,32.98185595386334
+1.4118708853910462,6.003042800612462,3.9968255952773095,0.7267789346532836
+0.21525181834957507,-3.321041549359367,-5.352746248495515,11.93444109619503
+4.80226153299567,9.818246112545182,4.936296097738831,3.5995719453822046
+9.71733974143089,0.1440918710436101,8.74993701189404,-34.917122745540794
+4.098687611436789,-9.75205878861841,7.980744101999381,-43.32805584620358
+-2.398060521804659,2.8278192128541733,-1.626174948927721,16.91539285950553
+5.398272903061114,7.583046908728093,2.758295974535457,4.437457748228852
+3.371527871466675,-5.430064318728407,2.1915998058530857,-16.03565826569788
+2.0863644528269365,0.10824916542728857,8.144465640869694,-25.094326089867696
+2.8255940202840684,-2.286321234798363,4.771241059098381,-18.000440202657604
+-8.150227640024978,-4.259315052105519,1.8923353680502952,-1.3930242667026356
+-6.067265316809651,3.6776254617776942,8.4817269440159,-10.278522746897893
+8.64017362219969,9.717801217085075,4.980672567111553,-0.9266647796977245
+-4.636910653452324,0.9373715699813872,4.978170771263397,-3.8217233698137143
+-7.940395120999431,2.953441321061362,-0.9370552302607145,21.291726783530805
+7.692709298116139,-5.485844206553388,-6.019643260327971,2.1873435652525455
+-6.485086441297707,7.06589989184231,-8.842925435171665,50.35981404591074
+5.036321300769028,2.0420739888497152,-4.368234397412891,15.435100617505809
+-2.203566631709222,-6.141030616852454,-1.822186931753599,-0.5890454529472771
+3.2620868350599768,7.851306022896178,-4.479265977335616,27.896949611024628
+6.402611257683294,-4.018677430646336,0.48600102750762986,-12.289355696825485
+5.378501224056757,4.355667003325474,-7.565417868242747,31.017195148404717
+2.0486633392332614,8.253411759540757,-3.966950647644751,29.555547834722987
+2.626017326894857,3.314924154867276,9.810418858378235,-22.85112181951592
+-0.04750452520510429,5.935777040113393,-0.3470621837504506,16.516617979443822
+-6.775500897482147,-0.8747563332852692,-2.758815934335188,16.55155644731519
+-5.130765599150095,8.959898235120185,1.1701541118251235,22.753375944830324
+9.607901921761815,-9.108821424255002,5.524296399378377,-41.93781490943017
+-2.9201254899877434,5.134928295361929,-9.896226148902585,43.58829658171542
+6.956501039100711,0.8359369151964895,-6.1636372998431295,16.225403196517274
+7.725179239543149,-4.913104095867496,-1.110476120153832,-9.936035489824537
+-6.142683379729563,1.4244393989902058,1.8529074318076262,5.554396424524908
+-2.0474061706133977,-1.2170618863263076,8.899325908803291,-23.596187786238964
+9.359523403637155,3.4124788823300065,-1.4222946765509725,2.4507844709064064
+-8.642800876507275,-9.508822574677566,2.9901775243378577,-16.775543378589024
+-2.470992582133973,5.1672327675732195,-8.753045094764744,40.855147394263106
+-7.756097982925145,5.227601844332813,-3.179199348468109,30.739018818654756
+5.393783291304004,-1.5186710515725927,-7.469139234639499,17.503383657767756
+-7.644671911438172,1.8115363641056241,-6.167155079348694,33.57677356652164
+6.557442460132911,-4.44188855380612,-6.368621306151785,7.435670420087931
+0.21009363927752744,-2.719754693698011,1.0885820356480096,-6.289562485886653
+-8.571672299069252,8.890348599509473,5.468260371802332,15.412904086362603
+7.872454219630789,-3.9905860234116357,0.9068940749874717,-16.017543419998542