def main(dist_file, pred_file, scoring_type):
# dist_file = '2015_10.json'
# pred_file = '../predictions.json'
# scoring_type = 'standard'
# Load dist data file
with open(dist_file) as f:
distdata = json.load(f)
# load prediction file
with open(pred_file) as f:
preddata = {d["player_id"]: d for d in json.load(f)}
# make scorer
scorer = make_scorer(base_type=scoring_type)
# score stats
preddata = {k: score_stats_dict(v, scorer=scorer) for k, v in preddata.iteritems()}
# add pred data to dist data
for k, v in distdata.iteritems():
if k in preddata.keys():
distdata[k].update({"player_info": preddata[k]})
else:
print(k)
# save updated dist data
with open(dist_file, "w") as f:
json.dump(distdata, f)
def score_stats_dict(stat_dict, scorer=make_scorer(base_type="standard")):
stat_dict.update(
{u"standard_score": sum([v * stat_dict[k] for k, v in scorer.iteritems() if k in stat_dict.keys()])}
)
return stat_dict
def main():
################################
### CONFIGURE
pred_week = 14 #None
db = nfldb.connect()
result_path='../results'
### LOAD DATA
# load train data
full_train, pipe, stats = load_feature_set(db)
# picks columns to model
lag_cols = [stat + '_lag' for stat in stats]
mean_cols = [stat + '_mean' for stat in stats]
other_cols = ['same_year_lag', 'played_lag']
infoColumns = ExtractColumns(like=[], exact=['year','week','time','player_id','full_name'])
row_info = infoColumns.fit_transform(X=full_train)
# load prediction data
pred_data, predict_i, pred_info, pred_yr_wk = prediction_feature_set(db, pipe, infoColumns, pred_week=pred_week)
##################################
### PREPARE DATA FOR TRAIN AND PREDICT
# train data with all columns
X_all = full_train
# prediction data with all columns
pred_all = pred_data.iloc[predict_i]
# which rows did players play
played_bool = full_train['played'] == 1
played_index = [i for i in range(X_all.shape[0]) if played_bool[i]]
# random split train and test
train_index, test_index = train_test_split_index(X_all.shape[0], test_size=0.1, seed=0)
feature_cols = lag_cols + mean_cols + other_cols
XColumns = ExtractColumns(like=feature_cols)
X = XColumns.fit_transform(X=X_all)
X_pred = XColumns.fit_transform(X=pred_all)
##################################
### SET UP & TRAIN KNN
# fit k nearest neighbors
k = 100
played_only = True
i_knn = played_index if played_only else range(X.shape[0])
#nn = NearestNeighbors(n_neighbors=k).fit(X.iloc[i_knn])
# regularization
reg = CoefScaler(linear_model=Ridge())
reg = reg.fit(X=X.iloc[i_knn], y = score_stats(X_all, make_scorer(base_type='standard')).iloc[i_knn])
X_reg = reg.transform(X.iloc[i_knn])
nn = NearestNeighbors(n_neighbors=k).fit(X_reg)
# returns tuple of (distances, indices of neighbors)
# for prediction set
#distance, neighbor = nn.kneighbors(X=X_pred)
X_reg_pred = reg.transform(X=X_pred)
distance, neighbor = nn.kneighbors(X=X_reg_pred)
##################################
### READ AND PLOT KNN RESULTS
nn_dict = {}
for check_i in range(pred_all.shape[0]):
# check neighbors
# check_nn is a data frame where the first row is the player
# and the rest of the rows are the nearest neighbors
check_nn = pred_all.iloc[[check_i],:].append(X_all.iloc[i_knn].iloc[neighbor[check_i,:]])
check_nn['StandardPoints'] = score_stats(check_nn, make_scorer(base_type='standard'))
check_nn['PPRPoints'] = score_stats(check_nn, make_scorer(base_type='ppr'))
nn_i = plot_knn(check_nn, save_image=True, plot_stat='StandardPoints', pred_yr_wk=pred_yr_wk, result_path=plot_image_path(result_path, pred_yr_wk), n_bins=25, bandwidth=2.5)
nn_dict.update(nn_i)
save_plot_data_json(nn_dict, result_path, pred_yr_wk)
