Kaggle数据处理

Brief introduction

import pandas as pd
from sklearn.model_selection import train_test_split

# Read the data
X_full = pd.read_csv('../input/train.csv', index_col='Id')
X_test_full = pd.read_csv('../input/test.csv', index_col='Id')

# Obtain target and predictors
y = X_full.SalePrice
features = ['LotArea', 'YearBuilt', '1stFlrSF', '2ndFlrSF', 'FullBath', 'BedroomAbvGr', 'TotRmsAbvGrd']
X = X_full[features].copy()
X_test = X_test_full[features].copy()

# Break off validation set from training data
X_train, X_valid, y_train, y_valid = train_test_split(X, y, train_size=0.8, test_size=0.2, random_state=0)


from sklearn.ensemble import RandomForestRegressor

# Define the models
model_1 = RandomForestRegressor(n_estimators=50, random_state=0)
model_2 = RandomForestRegressor(n_estimators=100, random_state=0)
model_3 = RandomForestRegressor(n_estimators=100, criterion='mae', random_state=0)
model_4 = RandomForestRegressor(n_estimators=200, min_samples_split=20, random_state=0)
model_5 = RandomForestRegressor(n_estimators=100, max_depth=7, random_state=0)

models = [model_1, model_2, model_3, model_4, model_5]


from sklearn.metrics import mean_absolute_error

# Function for comparing different models
def score_model(model, X_t=X_train, X_v=X_valid, y_t=y_train, y_v=y_valid):
    model.fit(X_t, y_t)
    preds = model.predict(X_v)
    return mean_absolute_error(y_v, preds)

for i in range(0, len(models)):
    mae = score_model(models[i])
    print("Model %d MAE: %d" % (i+1, mae))

# Fit the model to the training data
my_model = RandomForestRegressor()
my_model.fit(X, y)

# Generate test predictions
preds_test = my_model.predict(X_test)

# Save predictions in format used for competition scoring
output = pd.DataFrame({'Id': X_test.index,
                       'SalePrice': preds_test})
output.to_csv('submission.csv', index=False)

Missing Data

• A Simple Option: Drop Columns with Missing Values
• A Better Option: Imputation
• An Extension To Imputation
  Imputation is the standard approach, and it usually works well. However, imputed values may be systematically above or below their actual values (which weren’t collected in the dataset). Or rows with missing values may be unique in some other way. In that case, your model would make better predictions by considering which values were originally missing.

import pandas as pd
from sklearn.model_selection import train_test_split

# Load the data
data = pd.read_csv('../input/melbourne-housing-snapshot/melb_data.csv')

# Select target
y = data.Price

# To keep things simple, we'll use only numerical predictors
melb_predictors = data.drop(['Price'], axis=1)
X = melb_predictors.select_dtypes(exclude=['object'])

# Divide data into training and validation subsets
X_train, X_valid, y_train, y_valid = train_test_split(X, y, train_size=0.8, test_size=0.2, random_state=0)

# Get names of columns with missing values
cols_with_missing = [col for col in X_train.columns
                     if X_train[col].isnull().any()]

# Approach 1
# Drop columns in training and validation data
reduced_X_train = X_train.drop(cols_with_missing, axis=1)
reduced_X_valid = X_valid.drop(cols_with_missing, axis=1)

print("MAE from Approach 1 (Drop columns with missing values):")
print(score_dataset(reduced_X_train, reduced_X_valid, y_train, y_valid))

# Approach 2
# Imputation
from sklearn.impute import SimpleImputer

my_imputer = SimpleImputer()
imputed_X_train = pd.DataFrame(my_imputer.fit_transform(X_train))
imputed_X_valid = pd.DataFrame(my_imputer.transform(X_valid))

# Imputation removed column names; put them back
imputed_X_train.columns = X_train.columns
imputed_X_valid.columns = X_valid.columns

print("MAE from Approach 2 (Imputation):")
print(score_dataset(imputed_X_train, imputed_X_valid, y_train, y_valid))

Categorical Variables

import pandas as pd
from sklearn.model_selection import train_test_split

# Read the data
X = pd.read_csv('../input/train.csv', index_col='Id') 
X_test = pd.read_csv('../input/test.csv', index_col='Id')

# Remove rows with missing target, separate target from predictors
X.dropna(axis=0, subset=['SalePrice'], inplace=True)
y = X.SalePrice
X.drop(['SalePrice'], axis=1, inplace=True)

# To keep things simple, we'll drop columns with missing values
cols_with_missing = [col for col in X.columns if X[col].isnull().any()] 
X.drop(cols_with_missing, axis=1, inplace=True)
X_test.drop(cols_with_missing, axis=1, inplace=True)

# Break off validation set from training data
X_train, X_valid, y_train, y_valid = train_test_split(X, y,
                                                      train_size=0.8, test_size=0.2,
                                                      random_state=0)

# Approach 1
# Label encoding
# All categorical columns
object_cols = [col for col in X_train.columns if X_train[col].dtype == "object"]

# Columns that can be safely label encoded
good_label_cols = [col for col in object_cols if 
                   set(X_train[col]) == set(X_valid[col])]
        
# Problematic columns that will be dropped from the dataset
bad_label_cols = list(set(object_cols)-set(good_label_cols))

from sklearn.preprocessing import LabelEncoder

# Drop categorical columns that will not be encoded
label_X_train = X_train.drop(bad_label_cols, axis=1)
label_X_valid = X_valid.drop(bad_label_cols, axis=1)

# Apply label encoder 
label_encoder = LabelEncoder()
for col in set(good_label_cols):
    label_X_train[col] = label_encoder.fit_transform(label_X_train[col])
    label_X_valid[col] = label_encoder.transform(label_X_valid[col])
print("MAE from Approach 2 (Label Encoding):") 
print(score_dataset(label_X_train, label_X_valid, y_train, y_valid))

# Get number of unique entries in each column with categorical data
object_nunique = list(map(lambda col: X_train[col].nunique(), object_cols))
d = dict(zip(object_cols, object_nunique))

# Approach 2
# One-hot encoding
# Columns that will be one-hot encoded
low_cardinality_cols = [col for col in object_cols if X_train[col].nunique() < 10]

# Columns that will be dropped from the dataset
high_cardinality_cols = list(set(object_cols)-set(low_cardinality_cols))

from sklearn.preprocessing import OneHotEncoder

# Use as many lines of code as you need!
OH_encoder = OneHotEncoder(handle_unknown='ignore',sparse=False)
OH_cols_train = pd.DataFrame(OH_encoder.fit_transform(X_train[low_cardinality_cols]))
OH_cols_valid = pd.DataFrame(OH_encoder.transform(X_valid[low_cardinality_cols]))

OH_cols_train.index = X_train.index
OH_cols_valid.index = X_valid.index

num_X_train = X_train.drop(object_cols, axis=1)
num_X_valid = X_train.drop(object_cols, axis=1)

OH_X_train = pd.concat([OH_cols_train, num_X_train], axis=1)
OH_X_valid = pd.concat([OH_cols_valid, num_X_valid], axis=1)