Linear regression solution RMSE 34k

linear-regression.py

@@ -0,0 +1,47 @@
+import pandas as pd
+from pandas import DataFrame
+from sklearn import preprocessing
+from sklearn.linear_model import LinearRegression
+import plotly.express as px
+
+
+col_names = ["price", "mileage", "year", "brand", "engine_type", "engine_cap"]
+col_names_in = ["mileage", "year", "brand", "engine_type", "engine_cap"]
+df_train = pd.read_csv("train/train.tsv", error_bad_lines=False, header=None, sep="\t", names=col_names)
+df = df_train.drop(df_train[df_train["price"] < 1000].index)
+dev0 = pd.read_csv("dev-0/in.tsv", error_bad_lines=False, header=None, sep="\t", names=col_names_in)
+testA = pd.read_csv("test-A/in.tsv", error_bad_lines=False, header=None, sep="\t", names=col_names_in)
+
+
+def preprocess_data(df: DataFrame) -> DataFrame:
+    """Prepare dataset to linear regression"""
+    df["brand"] = df["brand"].str.lower()
+    scaler = preprocessing.StandardScaler()
+    df[["mileage", "year", "engine_cap"]] = scaler.fit_transform(df[["mileage", "year", "engine_cap"]])
+    enc = preprocessing.LabelEncoder()
+    enc.fit(df[["brand"]])
+    df[["brand"]] = enc.transform(df[["brand"]])
+
+    enc.fit(df["engine_type"])
+    df[["engine_type"]] = enc.transform(df[["engine_type"]])
+
+    return df
+
+
+df_train = preprocess_data(df_train)
+dev0 = preprocess_data(dev0)
+testA = preprocess_data(testA)
+
+fig = px.imshow(df_train.corr())
+fig.show()
+
+Y_train = df_train["price"]
+
+lm_model = LinearRegression()
+lm_model.fit(df_train[["mileage", "year", "brand",  "engine_cap"]], Y_train)
+
+dev0_predicted = lm_model.predict(dev0[["mileage", "year", "brand", "engine_cap"]])
+testA_predicted = lm_model.predict(testA[["mileage", "year", "brand", "engine_cap"]])
+
+pd.Series(dev0_predicted).to_csv("dev-0/out.tsv", sep="\t", index=False, header=False)
+pd.Series(testA_predicted).to_csv("test-A/out.tsv", sep="\t", index=False, header=False)