def dow_analyze(test_df, model, col, period_from, period_to):
validate_data = test_df[(test_df['visit_date'] >= period_from)
& (test_df["visit_date"] <= period_to)]
validate_data = validate_data[col]
score_list = []
for dow_num in range(7):
print("-" * 40)
print("dow= ", dow_num)
dowed_data = validate_data[validate_data["dow"] == dow_num]
print(dowed_data["visitors"].describe())
x_valid = dowed_data.drop('visitors', axis=1)
y_valid = model.predict(x_valid)
print(pd.DataFrame(y_valid).describe())
validation_score = custom_metrics.rmse(dowed_data["visitors"], y_valid)
score_list.append(validation_score)
print(score_list)
def split_train_skt(df, col, period_list, model):
models = []
score = 0.0
for period in period_list:
train = cut_input(df, period[0], period[1])
test = cut_input(df, period[2], period[3])
model.fit(train[col], train['visitors'])
y_pred = model.predict(test[col])
this_score = custom_metrics.rmse(test["visitors"], y_pred)
print(this_score)
score = score + this_score
models.append(model)
score = score / len(period_list)
print("Average score:")
print(score)
return models
def validate(test_df,
model,
col,
period_from,
period_to,
verbose=False,
save_model=False,
save_name=None):
validate_data = test_df[(test_df['visit_date'] >= period_from)
& (test_df["visit_date"] <= period_to)]
if verbose:
print("-" * 40)
print(period_from, " to ", period_to)
print(validate_data["visitors"].describe())
x_valid = validate_data[col].drop('visitors', axis=1)
y_valid = model.predict(x_valid)
if verbose:
print(pd.DataFrame(y_valid).describe())
validation_score = custom_metrics.rmse(validate_data["visitors"], y_valid)
print(validation_score)
if save_model:
save_prediction(validate_data, y_valid, save_name)
def store_analyze(test_df, model, col, period_from, period_to):
validate_data = test_df[(test_df['visit_date'] >= period_from)
& (test_df["visit_date"] <= period_to)]
validate_data = validate_data[col]
x_valid = validate_data.drop("visitors", axis=1)
y_valid = model.predict(x_valid)
validate_data["predicted"] = y_valid
# print(validate_data.head())
ret_list = []
for air_store_num in range(812):
single_store = validate_data[validate_data["air_store_num"] ==
air_store_num]
if single_store.empty:
print("whoops:", air_store_num)
continue
validate_score = custom_metrics.rmse(single_store["visitors"],
single_store["predicted"])
ret_list.append([air_store_num, validate_score])
ret_df = pd.DataFrame(ret_list, columns=["air_store_num", "score"])
return ret_df
def validate(df,
actual_col_name,
validate_col_name,
period_list=None,
verbose=False):
if period_list is None:
period_list = pocket_periods.get_six_week_period_list()
score_list = []
for period_from, period_to in period_list:
validate_data = df[(df['visit_date'] >= period_from)
& (df["visit_date"] <= period_to)]
validation_score = custom_metrics.rmse(
validate_data[actual_col_name], validate_data[validate_col_name])
score_list.append(validation_score)
if verbose:
print("score from ", period_from, " to ", period_to, " is:")
print(validation_score)
print("average score for", validate_col_name, " is:")
average_score = sum(score_list) / float(len(score_list))
print(average_score)
print("-" * 40)
w2_good = get_joined_model(good_filenames)
short_filenames = get_filenames(prefix_w2, "_short.csv")
w2_short = get_joined_model(short_filenames)
out_filenames = get_filenames(prefix_w2, "_out.csv")
w2_out = get_joined_model(out_filenames)
nores_filenames = get_filenames(prefix_w2, "_no_res.csv")
w2_nores = get_joined_model(nores_filenames)
print("Loaded data")
# print(w2_normal["prediction"].count())
# print(w2_good["prediction"].count())
# print(w2_short["prediction"].count())
# print(w2_out["prediction"].count())
# print(w2_nores["prediction"].count())
print("-" * 40)
normal_score = custom_metrics.rmse(w2_normal["actual_log"],
w2_normal["prediction"])
short_score = custom_metrics.rmse(w2_short["actual_log"],
w2_short["prediction"])
out_score = custom_metrics.rmse(w2_out["actual_log"], w2_out["prediction"])
nores_score = custom_metrics.rmse(w2_nores["actual_log"],
w2_nores["prediction"])
print("normal=", normal_score)
print("short=", short_score)
print("out=", out_score)
print("nores=", nores_score)
print("-" * 40)
df = pd.merge(w2_normal,
w2_short,
how="left",
on=["air_store_id", "visit_date"],
w2_short = pd.read_csv('../output/p1_w2_0416_0422_short_train.csv')
print("Loaded data")
print(all_model["actual"].count())
print(w2_model["actual"].count())
print(w2_good["actual"].count())
print(w2_short["actual"].count())
print("-" * 40)
df = pd.merge(all_model,
w2_model,
on=["air_store_id", "visit_date"],
suffixes=["_all", "_w2"])
# print(df.describe())
all_score = custom_metrics.rmse(df["actual_log_all"], df["prediction_all"])
w2_score = custom_metrics.rmse(df["actual_log_all"], df["prediction_w2"])
print("all=", all_score)
print("w2=", w2_score)
df["averaged"] = df["prediction_all"] * 0.1 + df["prediction_w2"] * 0.9
avg_score = custom_metrics.rmse(df["actual_log_all"], df["averaged"])
print("all+w2=", avg_score)
df = pd.merge(df,
w2_good,
on=["air_store_id", "visit_date"],
how="left",
suffixes=["", "_good"])
df["with_good"] = np.where(df["prediction"].isnull(), df["prediction_w2"],
df["prediction"])