인프런 커뮤니티 질문&답변

import pandas as pd

train = pd.read_csv("train.csv")

test = pd.read_csv("test.csv")

train.isnull().sum()

train =train.drop(["name", "host_name", "last_review"], axis=1)

train["reviews_per_month"] = train["reviews_per_month"].fillna(train["reviews_per_month"].mean())

test =test.drop(["name", "host_name", "last_review"], axis=1)

test["reviews_per_month"] = test["reviews_per_month"].fillna(test["reviews_per_month"].mean())

cols = train.select_dtypes(include = "object").columns

from sklearn.preprocessing import LabelEncoder

for col in cols:

le = LabelEncoder()

train[col] = le.fit_transform(train[col])

test[col] = le.transform(test[col])

from sklearn.model_selection import train_test_split

X_tr, X_val, y_tr, y_val = train_test_split(train.drop("price", axis =1 ), train["price"], test_size=0.1, random_state=2022)

from sklearn.ensemble import RandomForestRegressor

rf = RandomForestRegressor()

rf.fit(X_tr, y_tr)

pred = rf.predict(X_val)

pred = rf.predict(test)

submit = pd.DataFrame({"id":test['id'], "price": pred})

submit.to_csv("990906.csv", index=False)

csv를 읽었더니

id price

34323697 259.01

29927138 115.78

이런식으로 price가 소수점으로 나오는데 어디 코드에서 틀린걸까요?