def gpu_load_performance_csv(performance_path, **kwargs):
""" Loads performance data
Returns
-------
GPU DataFrame
"""
chronometer = Chronometer.makeStarted()
cols = [
"loan_id",
"monthly_reporting_period",
"servicer",
"interest_rate",
"current_actual_upb",
"loan_age",
"remaining_months_to_legal_maturity",
"adj_remaining_months_to_maturity",
"maturity_date",
"msa",
"current_loan_delinquency_status",
"mod_flag",
"zero_balance_code",
"zero_balance_effective_date",
"last_paid_installment_date",
"foreclosed_after",
"disposition_date",
"foreclosure_costs",
"prop_preservation_and_repair_costs",
"asset_recovery_costs",
"misc_holding_expenses",
"holding_taxes",
"net_sale_proceeds",
"credit_enhancement_proceeds",
"repurchase_make_whole_proceeds",
"other_foreclosure_proceeds",
"non_interest_bearing_upb",
"principal_forgiveness_upb",
"repurchase_make_whole_proceeds_flag",
"foreclosure_principal_write_off_amount",
"servicing_activity_indicator",
]
dtypes = OrderedDict([
("loan_id", "int64"),
("monthly_reporting_period", "date"),
("servicer", "category"),
("interest_rate", "float64"),
("current_actual_upb", "float64"),
("loan_age", "float64"),
("remaining_months_to_legal_maturity", "float64"),
("adj_remaining_months_to_maturity", "float64"),
("maturity_date", "date"),
("msa", "float64"),
("current_loan_delinquency_status", "int32"),
("mod_flag", "category"),
("zero_balance_code", "category"),
("zero_balance_effective_date", "date"),
("last_paid_installment_date", "date"),
("foreclosed_after", "date"),
("disposition_date", "date"),
("foreclosure_costs", "float64"),
("prop_preservation_and_repair_costs", "float64"),
("asset_recovery_costs", "float64"),
("misc_holding_expenses", "float64"),
("holding_taxes", "float64"),
("net_sale_proceeds", "float64"),
("credit_enhancement_proceeds", "float64"),
("repurchase_make_whole_proceeds", "float64"),
("other_foreclosure_proceeds", "float64"),
("non_interest_bearing_upb", "float64"),
("principal_forgiveness_upb", "float64"),
("repurchase_make_whole_proceeds_flag", "category"),
("foreclosure_principal_write_off_amount", "float64"),
("servicing_activity_indicator", "category"),
])
print(performance_path)
performance_table = pyblazing.create_table(
table_name="perf",
type=get_type_schema(performance_path),
path=performance_path,
delimiter="|",
names=cols,
dtypes=get_dtype_values(dtypes),
skip_rows=1,
)
Chronometer.show(chronometer, "Read Performance CSV")
return performance_table
def gpu_load_acquisition_csv(acquisition_path, **kwargs):
""" Loads acquisition data
Returns
-------
GPU DataFrame
"""
chronometer = Chronometer.makeStarted()
cols = [
"loan_id",
"orig_channel",
"seller_name",
"orig_interest_rate",
"orig_upb",
"orig_loan_term",
"orig_date",
"first_pay_date",
"orig_ltv",
"orig_cltv",
"num_borrowers",
"dti",
"borrower_credit_score",
"first_home_buyer",
"loan_purpose",
"property_type",
"num_units",
"occupancy_status",
"property_state",
"zip",
"mortgage_insurance_percent",
"product_type",
"coborrow_credit_score",
"mortgage_insurance_type",
"relocation_mortgage_indicator",
]
dtypes = OrderedDict([
("loan_id", "int64"),
("orig_channel", "category"),
("seller_name", "category"),
("orig_interest_rate", "float64"),
("orig_upb", "int64"),
("orig_loan_term", "int64"),
("orig_date", "date"),
("first_pay_date", "date"),
("orig_ltv", "float64"),
("orig_cltv", "float64"),
("num_borrowers", "float64"),
("dti", "float64"),
("borrower_credit_score", "float64"),
("first_home_buyer", "category"),
("loan_purpose", "category"),
("property_type", "category"),
("num_units", "int64"),
("occupancy_status", "category"),
("property_state", "category"),
("zip", "int64"),
("mortgage_insurance_percent", "float64"),
("product_type", "category"),
("coborrow_credit_score", "float64"),
("mortgage_insurance_type", "float64"),
("relocation_mortgage_indicator", "category"),
])
print(acquisition_path)
acquisition_table = pyblazing.create_table(
table_name="acq",
type=get_type_schema(acquisition_path),
path=acquisition_path,
delimiter="|",
names=cols,
dtypes=get_dtype_values(dtypes),
skip_rows=1,
)
Chronometer.show(chronometer, "Read Acquisition CSV")
return acquisition_table
final_cpu_df_label = pd.concat(
[final_cpu_df_label, cpu_df_label])
final_cpu_df_data = pd.concat([final_cpu_df_data, cpu_df_data])
xgb_convert_end_time = time.time()
all_xgb_convert_times.append(xgb_convert_end_time -
xgb_convert_start_time)
data_train, data_test, label_train, label_test = train_test_split(
final_cpu_df_data, final_cpu_df_label, test_size=0.20, random_state=42)
xgdf_train = xgb.DMatrix(data_train, label_train)
xgdf_test = xgb.DMatrix(data_test, label_test)
chronometerTrain1 = Chronometer.makeStarted()
startTime = time.time()
bst = xgb.train(dxgb_gpu_params,
xgdf_train,
num_boost_round=dxgb_gpu_params["nround"])
Chronometer.show(chronometerTrain1, "Train 1")
chronometerPredict1 = Chronometer.makeStarted()
preds = bst.predict(xgdf_test)
Chronometer.show(chronometerPredict1, "Predict 1")
labels = xgdf_test.get_label()
print("prediction error=%f" %
(sum(1 for i in range(len(preds)) if int(preds[i] > 0.5) != labels[i]) /
float(len(preds))))
