LinearRegression

main.py

@@ -1,5 +1,9 @@
 import pandas as pd
 import matplotlib.pyplot as plt
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+import numpy as np
+
 
 # Read column names
 col_names = []
@@ -13,47 +17,64 @@ test = pd.read_table('test-A/in.tsv', error_bad_lines=False,
                      header=None,  names=col_names[1:])
 train = pd.read_table('train/train.tsv', error_bad_lines=False,
                       header=None,  names=col_names)
-test_expected = pd.read_table('dev-0/expected.tsv', error_bad_lines=False,
+dev_expected = pd.read_table('dev-0/expected.tsv', error_bad_lines=False,
                              header=None)
 
-# Create dummies for brand
-train = pd.get_dummies(train, columns=['engineType'])
+# Create dummies for columns
+for c in train.select_dtypes(include=object).columns.values:
+    train[c] = train[c].astype("category").cat.codes
+for c in dev.select_dtypes(include=object).columns.values:
+    dev[c] = dev[c].astype("category").cat.codes
+for c in test.select_dtypes(include=object).columns.values:
+    test[c] = test[c].astype("category").cat.codes
 
 # Sprawdzanie ile jest odstających wartości dla price
-fig, ax = plt.subplots(1, 2)
-fig.set_figheight(15)
-fig.set_figwidth(20)
-ax[0].boxplot(train['price'])
-ax[0].set_title('price')
-ax[1].boxplot(train['mileage'])
-ax[1].set_title('mileage')
-plt.show()
+# fig, ax = plt.subplots(1, 2)
+# fig.set_figheight(15)
+# fig.set_figwidth(20)
+# ax[0].boxplot(train['price'])
+# ax[0].set_title('price')
+# ax[1].boxplot(train['mileage'])
+# ax[1].set_title('mileage')
+# plt.show()
 
 # Usunięcie odstających wartości
 priceMin = 0
 for price in train['price']:
     if price < 1000:
         priceMin += 1
-print("Price min cut: " + str(priceMin))
+# print("Price min cut: " + str(priceMin))
 
 priceMax = 0
 for price in train['price']:
     if price > 1000000:
         priceMin += 1
-print("Price max cut: " + str(priceMax))
+# print("Price max cut: " + str(priceMax))
 
 mileageMin = 0
 for m in train['mileage']:
     if m < 100:
         mileageMin += 1
-print("Mileage min cut: " + str(mileageMin))
+# print("Mileage min cut: " + str(mileageMin))
 
 train = train.loc[(train['price'] > 1000)]
 train = train.loc[(train['mileage'] > 100)]
 
 # Split train set to X and Y
-X = train.loc[:, train.columns != 'price']
-Y = train['price']
+X_train = train.loc[:, train.columns != 'price']
+Y_train = train['price']
 
-# print(train)
-# print(col_names)
+# Create Linear regresion model
+clf = LinearRegression().fit(X_train, Y_train)
+
+# # Predict
+dev_p = clf.predict(dev)
+test_p = clf.predict(test)
+
+# # Accuracy
+score = mean_squared_error(dev_p, dev_expected, squared=False)
+print("RMSE: " + str(score))
+
+# # Save to files
+dev_p.tofile('./dev-0/out.tsv', sep='\n')
+test_p.tofile('./test-A/out.tsv', sep='\n')