linear sklearn v2

dev0_rmse.txt

@@ -1 +1 @@
-1013603084.8408571
+1165319253.2984157

main.py

@@ -4,38 +4,33 @@ from sklearn.linear_model import LinearRegression
 from sklearn.metrics import mean_squared_error
 import numpy as np
 
-df = pd.read_csv("train/train.tsv", header=None, sep="\t", error_bad_lines=False)
-dev0 = pd.read_csv("dev-0/in.tsv", header=None, sep="\t", error_bad_lines=False)
-testA = pd.read_csv("test-A/in.tsv", header=None, sep="\t", error_bad_lines=False)
-expected = pd.read_csv("dev-0/expected.tsv", header=None, sep="\t", error_bad_lines=False)
+df = pd.read_csv("train/train.tsv", header=None, sep="\t", error_bad_lines=False, names=['price', 'mileage', 'year',
+                                                                                         'brand', 'engineType',
+                                                                                         'engineCapacity'])
+dev0 = pd.read_csv("dev-0/in.tsv", header=None, sep="\t", error_bad_lines=False, names=['mileage', 'year',
+                                                                                        'brand', 'engineType',
+                                                                                        'engineCapacity'])
+testA = pd.read_csv("test-A/in.tsv", header=None, sep="\t", error_bad_lines=False, names=['mileage', 'year',
+                                                                                          'brand', 'engineType',
+                                                                                          'engineCapacity'])
+expected = pd.read_csv("dev-0/expected.tsv", header=None, sep="\t", error_bad_lines=False, names=['price'])
 
-all_df = df.copy()
-test_dev0 = dev0.copy()
-test_dev0.insert(0, "dum", 0, True)
-test_dev0 = test_dev0.rename(columns={"dum": 0, 0: 1, 1: 2, 2: 3, 3: 4, 4: 5, 5: 6})
-all_df = all_df.append(test_dev0, ignore_index=True)
+df = df[['price', 'year', 'mileage', 'engineCapacity']]
 
-test_testA = testA.copy()
-test_testA.insert(0, "dum", 0, True)
-test_testA = test_testA.rename(columns={"dum": 0, 0: 1, 1: 2, 2: 3, 3: 4, 4: 5, 5: 6})
-all_df = all_df.append(test_testA, ignore_index=True)
-all_df = pd.get_dummies(all_df, columns=[3, 4])
+min_val = np.min(df)
+max_val = np.max(df)
+df = (df - min_val) / (max_val - min_val)
 
-min_val = np.min(all_df)
-max_val = np.max(all_df)
-all_df = (all_df - min_val) / (max_val - min_val)
-
-dummy_df = all_df[:len(df)]
-dummy_dev0 = all_df[len(df):len(df) + len(dev0)]
-dummy_testA = all_df[len(df) + len(dev0):]
-
-X = dummy_df[dummy_df.columns[1:]]
-Y = dummy_df[dummy_df.columns[:1]]
+Y = df[['price']]
+X = df[['year', 'mileage', 'engineCapacity']]
 
 model = LinearRegression().fit(X, Y)
 
-predicted_dev0 = model.predict(dummy_dev0[dummy_dev0.columns[1:]])
-predicted_testA = model.predict(dummy_testA[dummy_testA.columns[1:]])
+dev0 = (dev0[['year', 'mileage', 'engineCapacity']] - min_val) / (max_val - min_val)
+testA = (testA[['year', 'mileage', 'engineCapacity']] - min_val) / (max_val - min_val)
+
+predicted_dev0 = model.predict(dev0[['year', 'mileage', 'engineCapacity']])
+predicted_testA = model.predict(testA[['year', 'mileage', 'engineCapacity']])
 
 with open("dev-0/out.tsv", "w") as file:
     for pred in predicted_dev0:
@@ -45,15 +40,18 @@ with open("test-A/out.tsv", "w") as file:
     for pred in predicted_testA:
         file.write(str(pred[0]) + "\n")
 
+
 predicted_denormalized = []
 for pred in predicted_dev0:
-    predicted_denormalized.append(pred[0] * (max_val[0] - min_val[0]) + min_val[0])
+    denorm = pred[0] * (max_val[0] - min_val[0]) + min_val[0]
+    predicted_denormalized.append(denorm)
 
 predicted_denormalized = DataFrame(predicted_denormalized, columns=['pred'])
 error = mean_squared_error(expected, predicted_denormalized)
 for exp, pred in zip(expected.values, predicted_denormalized.values):
     print(exp, pred)
-    
+
 f = open("dev0_rmse.txt", "w")
 f.write(str(error))
-f.close()
+f.close()
+print(error)