81 lines
2.3 KiB
Python
81 lines
2.3 KiB
Python
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 = []
|
|
with open('names') as f:
|
|
col_names = f.read().strip().split('\t')
|
|
|
|
# Read data
|
|
dev = pd.read_table('dev-0/in.tsv', error_bad_lines=False,
|
|
header=None, names=col_names[1:])
|
|
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)
|
|
dev_expected = pd.read_table('dev-0/expected.tsv', error_bad_lines=False,
|
|
header=None)
|
|
|
|
# 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()
|
|
|
|
# Usunięcie odstających wartości
|
|
priceMin = 0
|
|
for price in train['price']:
|
|
if price < 1000:
|
|
priceMin += 1
|
|
# print("Price min cut: " + str(priceMin))
|
|
|
|
priceMax = 0
|
|
for price in train['price']:
|
|
if price > 1000000:
|
|
priceMin += 1
|
|
# print("Price max cut: " + str(priceMax))
|
|
|
|
mileageMin = 0
|
|
for m in train['mileage']:
|
|
if m < 100:
|
|
mileageMin += 1
|
|
# 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 = train.loc[:, train.columns != 'price']
|
|
Y_train = train['price']
|
|
|
|
# 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')
|