def train_and_predict(train_df, test_df):
# Data Cleaning
# clean the data
cleaner = DataCleaner()
cleaner.columns_with_no_nan(train_df)
cleaner.columns_with_no_nan(test_df)
train_df = cleaner.drop_columns(train_df)
train_df = cleaner.resolve_nan(train_df)
test_df = cleaner.drop_columns(test_df)
test_df = cleaner.resolve_nan(test_df)
# features engineering
train_df, test_df = engineer_features(train_df, test_df)
# train the model from Model
model = Classifier()
model = model.model()
# LabelEncoding/OneHotEncoding?
train_df = model.encode(train_df)
test_df = model.encode(test_df)
# training progress and results
model = model.train(model, train_df)
# predict on test_df with predict method from Model
y_test = model.predict(model, test_df)
return y_test
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.metrics import mean_squared_error, r2_score, f1_score
from question_query import create_questions_df
from answer_query import create_answers_df
from data_cleaning import DataCleaner
from model_tester import FindOptimalModels
if __name__ == '__main__':
numrows = 1e6
print("Connecting and getting ~{}".format(numrows))
a = create_answers_df(numrows)
print("Got rows, cleaning data")
a_train_dc = DataCleaner(a, questions=False, training=True,
simple_regression=True, time_split=False,
normalize=False)
A, b = a_train_dc.get_clean()
default_models = [RandomForestRegressor, GradientBoostingRegressor]
param_dict = {'rf': {'n_estimators': [50, 100, 5000], 'max_depth':
[2, 3, 5]},
'gbr': {'learning_rate': [.001, .01, .1, .2], 'max_depth':
[2, 3, 5], 'n_estimators': [50, 100, 5000]}}
print('Finding optimal models')
finder = FindOptimalModels(A, b, question=False, time_split=False)
finder.baseline_model()
fitted_models = finder.run_default_models(default_models)
print("starting grid search")
opt_params = finder.run_grid_search(fitted_models, param_dict)
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.metrics import mean_squared_error, r2_score, f1_score
from question_query import create_questions_df
from answer_query import create_answers_df
from data_cleaning import DataCleaner
from model_tester import FindOptimalModels
if __name__ == '__main__':
numrows = 1e6
print("Connecting and getting ~{}".format(numrows))
q = create_questions_df(numrows)
print("Got rows, cleaning data")
q_train_dc = DataCleaner(q,
questions=True,
training=True,
simple_regression=True,
time_split=True,
normalize=True)
X, y = q_train_dc.get_clean()
default_models = [RandomForestRegressor, GradientBoostingRegressor]
param_dict = {
'rf': {
'n_estimators': [50, 100, 5000],
'max_depth': [2, 3, 5]
},
'gbr': {
'learning_rate': [.001, .01, .1, .2],
'max_depth': [2, 3, 5],
'n_estimators': [50, 100, 5000]
gps = pd.read_csv('./data/Longitud_Latitud.csv')
# Create sub_area categorical with all levels shared
# between train and test to avoid errors
test['price_doc'] = -99
merged = pd.concat([train, test], axis=0)
merged = merged.merge(gps, how='left', on='sub_area')
merged['sub_area'] = merged.sub_area.astype('category')
train = merged[merged.price_doc != -99]
test = merged[merged.price_doc == -99]
test.pop('price_doc')
macro = pd.read_csv('data/macro.csv', parse_dates=['timestamp'])
train = train.merge(macro, how='left', on='timestamp', suffixes=('_train', '_macro'))
# Clean
dc = DataCleaner(data=train, sample_rate=0.3)
data, y = dc.clean()
y = np.array(y)
y = np.log(y+1)
# Train / test split
data_train, data_test, y_train, y_test = train_test_split(data, y, random_state=77)
house_ids_test = data_test.id
# Featurize training data set
feat_train = Featurizer()
X_train = feat_train.featurize(data_train)
# Grid search tune all estimators
ms = ModelSelector()
print ' # {:s} | X_train shape: {:s}'.format(now(), X_train.shape)
import numpy as np
from data_cleaning import DataCleaner
from features_engineering import FeatureExtractor
from model_selection import ModelSelector
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
plt.interactive(True)
if __name__ == '__main__':
# read and clean the data
dc = DataCleaner()
data = dc.clean()
# Debug transformations
# data.to_csv('./data/debug.csv', index=False, encoding='latin1')
# assert False
# separate target variable
target = data.pop('Target')
# train test split
data_train, data_test, target_train, target_test = train_test_split(
data, target)
# featurize data
featurizer = FeatureExtractor()
X_train = featurizer.featurize(data_train)
X_test = featurizer.featurize(data_test)
# Convert to numpy arrays
y_train = np.array(target_train)
test = pd.read_csv('./data/test.csv')
gps = pd.read_csv('./data/Longitud_Latitud.csv')
# Create sub_area categorical with all levels shared
# between train and test to avoid errors
test['price_doc'] = -99
merged = pd.concat([train, test], axis=0)
merged = merged.merge(gps, how='left', on='sub_area')
merged['sub_area'] = merged.sub_area.astype('category')
train = merged[merged.price_doc != -99]
train = train.merge(macro,
how='left',
on='timestamp',
suffixes=('_train', '_macro'))
dc = DataCleaner(data=train)
train, y = dc.clean()
y = np.array(y)
y = np.log(y + 1)
# Featurize training data set
feat_train = Featurizer()
train = feat_train.featurize(train)
print 'train shape', train.shape
# # Remove all categorical variables for now
# mask = ~(train.dtypes == 'object').values
# train = train.iloc[:, mask]
# print 'train shape with only numerical features', train.shape