def cross_validate(matrix,
identifiers,
features,
id2name,
model,
n_folds=3,
seed=None):
"""Use data from all year deltas > target_delta to predict scores."""
feature_cols = [
idx for idx, (feat, delta) in enumerate(features) if delta != 0
]
objective_index = features.index(('fantasy_points', 0))
def get_features_objective(_matrix):
X = _matrix[:, feature_cols]
y = _matrix[:, objective_index]
return X, y
accum_test_identifiers = []
accum_test_scores = []
accum_test_preds = []
for fold, (train_index, test_index) in \
enumerate(KFold(n=matrix.shape[0], n_folds=n_folds, shuffle=True,
random_state=seed)):
imputer = Imputer()
scaler = StandardScaler() # Need to standardize for eg SVR
train_matrix = matrix[train_index, :]
test_matrix = matrix[test_index, :]
imputer.fit(train_matrix)
train_imputed = scaler.fit_transform(imputer.transform(train_matrix))
test_imputed = scaler.transform(imputer.transform(test_matrix))
X_train, y_train = get_features_objective(train_imputed)
model.fit(X_train, y_train)
X_test, y_test = get_features_objective(test_imputed)
y_pred = model.predict(X_test)
test_identifiers = [identifiers[idx] for idx in test_index]
accum_test_identifiers.extend(test_identifiers)
accum_test_scores.extend(y_test)
accum_test_preds.extend(y_pred)
pos_ranks_true = position_ranking_lists(accum_test_identifiers,
accum_test_scores, id2name)
pos_ranks_pred = position_ranking_lists(accum_test_identifiers,
accum_test_preds, id2name)
taus = compute_taus(pos_ranks_true, pos_ranks_pred)
for deltapos in sorted(taus, key=lambda x: (x[1], x[0])):
print deltapos, taus[deltapos]
return
def main():
id2year2stats = load_files(
{year: 'fant%d.csv' % year
for year in xrange(2008, 2013)}, SPECIAL_CASE_TRADES)
def id_to_useful_name(id):
year2stats = id2year2stats[id]
any_year = year2stats[year2stats.keys()[0]]
return (any_year['Name'], any_year['Tm'], any_year['FantasyFantPos'])
current_players = set(id for id in id2year2stats
if BASE_YEAR - 1 in id2year2stats[id])
matrix, identifiers, features = construct_feature_matrix(id2year2stats)
id2name = {
ident[ID]: id_to_useful_name(ident[ID])
for ident in identifiers
}
from sklearn import linear_model
from sklearn import ensemble
from sklearn import svm
seed = randint(0, 2**32 - 1)
for model in [
linear_model.LinearRegression(),
linear_model.Ridge(),
ensemble.RandomForestRegressor(),
ensemble.ExtraTreesRegressor(),
ensemble.AdaBoostRegressor(),
ensemble.GradientBoostingRegressor(),
svm.SVR(),
svm.NuSVR(),
]:
print str(model).split('(')[0]
cross_validate(matrix,
identifiers,
features,
id2name,
model,
n_folds=10,
seed=seed)
print
model = ensemble.RandomForestRegressor()
current_predictions, current_ids = \
predict_current_year(matrix, identifiers, features, id2name, model)
current_predictions, current_ids = zip(
*[(pred, ident)
for pred, ident in zip(current_predictions, current_ids)
if ident[ID] in current_players])
current_predicted_ranks = position_ranking_lists(current_ids,
current_predictions,
id2name)
dump_predictions(current_predicted_ranks)
return
def cross_validate(matrix, identifiers, features, id2name, model, n_folds=3, seed=None):
"""Use data from all year deltas > target_delta to predict scores."""
feature_cols = [idx for idx, (feat, delta) in enumerate(features) if delta != 0]
objective_index = features.index(("fantasy_points", 0))
def get_features_objective(_matrix):
X = _matrix[:, feature_cols]
y = _matrix[:, objective_index]
return X, y
accum_test_identifiers = []
accum_test_scores = []
accum_test_preds = []
for fold, (train_index, test_index) in enumerate(
KFold(n=matrix.shape[0], n_folds=n_folds, shuffle=True, random_state=seed)
):
imputer = Imputer()
scaler = StandardScaler() # Need to standardize for eg SVR
train_matrix = matrix[train_index, :]
test_matrix = matrix[test_index, :]
imputer.fit(train_matrix)
train_imputed = scaler.fit_transform(imputer.transform(train_matrix))
test_imputed = scaler.transform(imputer.transform(test_matrix))
X_train, y_train = get_features_objective(train_imputed)
model.fit(X_train, y_train)
X_test, y_test = get_features_objective(test_imputed)
y_pred = model.predict(X_test)
test_identifiers = [identifiers[idx] for idx in test_index]
accum_test_identifiers.extend(test_identifiers)
accum_test_scores.extend(y_test)
accum_test_preds.extend(y_pred)
pos_ranks_true = position_ranking_lists(accum_test_identifiers, accum_test_scores, id2name)
pos_ranks_pred = position_ranking_lists(accum_test_identifiers, accum_test_preds, id2name)
taus = compute_taus(pos_ranks_true, pos_ranks_pred)
for deltapos in sorted(taus, key=lambda x: (x[1], x[0])):
print deltapos, taus[deltapos]
return
def main():
id2year2stats = load_files(
{year: 'fant%d.csv' % year for year in xrange(2008, 2013)},
SPECIAL_CASE_TRADES)
def id_to_useful_name(id):
year2stats = id2year2stats[id]
any_year = year2stats[year2stats.keys()[0]]
return (any_year['Name'], any_year['Tm'],
any_year['FantasyFantPos'])
current_players = set(id for id in id2year2stats if BASE_YEAR - 1 in
id2year2stats[id])
matrix, identifiers, features = construct_feature_matrix(id2year2stats)
id2name = {ident[ID]: id_to_useful_name(ident[ID]) for ident in
identifiers}
from sklearn import linear_model
from sklearn import ensemble
from sklearn import svm
seed = randint(0, 2**32 - 1)
for model in [linear_model.LinearRegression(),
linear_model.Ridge(),
ensemble.RandomForestRegressor(),
ensemble.ExtraTreesRegressor(),
ensemble.AdaBoostRegressor(),
ensemble.GradientBoostingRegressor(),
svm.SVR(),
svm.NuSVR(),
]:
print str(model).split('(')[0]
cross_validate(matrix, identifiers, features, id2name, model,
n_folds=10, seed=seed)
print
model = ensemble.RandomForestRegressor()
current_predictions, current_ids = \
predict_current_year(matrix, identifiers, features, id2name, model)
current_predictions, current_ids = zip(
*[(pred, ident) for pred, ident
in zip(current_predictions, current_ids)
if ident[ID] in current_players])
current_predicted_ranks = position_ranking_lists(
current_ids, current_predictions, id2name)
dump_predictions(current_predicted_ranks)
return
