aialenti’s gists

aialenti / list of cities

Created December 14, 2019 16:25

	['Tokyo', 'New York', 'Mexico City', 'Mumbai', 'São Paulo', 'Delhi',
	'Shanghai', 'Kolkata', 'Los Angeles', 'Dhaka', 'Buenos Aires',
	'Karachi', 'Cairo', 'Rio de Janeiro', 'Ōsaka', 'Beijing', 'Manila',
	'Moscow', 'Istanbul', 'Paris', 'Seoul', 'Lagos', 'Jakarta',
	'Guangzhou', 'Chicago', 'London', 'Lima', 'Tehran', 'Kinshasa',
	'Bogotá', 'Shenzhen', 'Wuhan', 'Hong Kong', 'Tianjin', 'Chennai',
	'Taipei', 'Bengalūru', 'Bangkok', 'Lahore', 'Chongqing', 'Miami',
	'Hyderabad', 'Dallas', 'Santiago', 'Philadelphia',
	'Belo Horizonte', 'Madrid', 'Houston', 'Ahmadābād',
	'Ho Chi Minh City', 'Washington', 'Atlanta', 'Toronto',

aialenti / other cities

Created December 14, 2019 16:39

	['Tokyo', 'New York', 'Mexico City', 'Mumbai', 'São Paulo', 'Delhi',
	'Shanghai', 'Kolkata', 'Los Angeles', 'Dhaka', 'Buenos Aires',
	'Karachi', 'Cairo', 'Rio de Janeiro', 'Ōsaka', 'Beijing', 'Manila',
	'Moscow', 'Istanbul', 'Paris', 'Seoul', 'Lagos', 'Jakarta',
	'Guangzhou', 'Chicago', 'London', 'Lima', 'Tehran', 'Kinshasa',
	'Bogotá', 'Shenzhen', 'Wuhan', 'Hong Kong', 'Tianjin', 'Chennai',
	'Taipei', 'Bengalūru', 'Bangkok', 'Lahore', 'Chongqing', 'Miami',
	'Hyderabad', 'Dallas', 'Santiago', 'Philadelphia',
	'Belo Horizonte', 'Madrid', 'Houston', 'Ahmadābād',
	'Ho Chi Minh City', 'Washington', 'Atlanta', 'Toronto',

aialenti / class.py

Last active December 14, 2019 17:49

aialenti / file.csv

Created January 25, 2020 15:16

	ID	y	X0	X1	X2	X3	X4	X5	X6	X8	X10	X11	X12	X13	X14	X15	X16	X17	X18	X19	X20	X21	X22	X23	X24	X26	X27	X28	X29	X30	X31	X32	X33	X34	X35	X36	X37	X38	X39	X40	X41	X42	X43	X44	X45	X46	X47	X48	X49	X50	X51	X52	X53	X54	X55	X56	X57	X58	X59	X60	X61	X62	X63	X64	X65	X66	X67	X68	X69	X70	X71	X73	X74	X75	X76	X77	X78	X79	X80	X81	X82	X83	X84	X85	X86	X87	X88	X89	X90	X91	X92	X93	X94	X95	X96	X97	X98	X99	X100	X101	X102	X103	X104	X105	X106	X107	X108	X109	X110	X111	X112	X113	X114	X115	X116	X117	X118	X119	X120	X122	X123	X124	X125	X126	X127	X128	X129	X130	X131	X132	X133	X134	X135	X136	X137	X138	X139	X140	X141	X142	X143	X144	X145	X146	X147	X148	X150	X151	X152	X153	X154	X155	X156	X157	X158	X159	X160	X161	X162	X163	X164	X165	X166	X167	X168	X169	X170	X171	X172	X173	X174	X175	X176	X177	X178	X179	X180	X181	X182	X183	X184	X185	X186	X187	X189	X190	X191	X192	X194	X195	X196	X197	X198	X199	X200	X201	X202	X203	X204	X205	X206	X207	X208	X209	X210	X211	X212	X213	X214	X215	X216	X217	X218	X219	X220	X221	X222	X223	X224	X225	X226	X227	X228	X229	X230	X231	X23

aialenti / preprocessing.py

Created January 30, 2020 22:19

	def preprocessing():
	# Read input data
	train = pd.read_csv("train.csv")
	categorical = ["X0", "X1", "X2", "X3", "X4", "X5", "X6", "X8"]

	# Convert categorical data
	for c in categorical:
	group_by = train.groupby(by=c)["y"].mean().reset_index().rename(columns={"y": "{}_converted".format(c)})
	train = pd.merge(train, group_by, how='inner', on=c)

aialenti / search_space.py

Last active February 2, 2020 18:10

	param_grid = {'learning_rate': [float(v) for v in np.arange(0.01, 0.25, 0.01)],
	'colsample_bytree': [float(v) for v in np.arange(0.8, 1.01, 0.1)],
	'subsample': [float(v) for v in np.arange(0.5, 1.01, 0.1)],
	'n_estimators': [int(v) for v in np.arange(100, 3000, 100)],
	'reg_alpha': [float(v) for v in np.arange(0.01, 0.5, 0.05)],
	'max_depth': [int(v) for v in np.arange(3, 14, 1)],
	'gamma': [int(v) for v in np.arange(0, 10, 2)]
	}

aialenti / grid_generator.py

Created February 2, 2020 18:10

	def get_grid_iterable():
	param_grid = {'learning_rate': [float(v) for v in np.arange(0.01, 0.25, 0.01)],
	'colsample_bytree': [float(v) for v in np.arange(0.8, 1.01, 0.1)],
	'subsample': [float(v) for v in np.arange(0.5, 1.01, 0.1)],
	'n_estimators': [int(v) for v in np.arange(100, 3000, 100)],
	'reg_alpha': [float(v) for v in np.arange(0.01, 0.5, 0.05)],
	'max_depth': [int(v) for v in np.arange(3, 14, 1)],
	'gamma': [int(v) for v in np.arange(0, 10, 2)]
	}
	grid_iter = []

aialenti / begin.py

Created February 2, 2020 18:33

	# Read input data
	X, y = preprocessing()

	# Create dataframe to collect the results
	tests_columns = ["test_nr", "cv_mean", "cv_min", "cv_max", "cv_median", "params"]
	test_id = 0
	tests = pd.DataFrame(columns=tests_columns)

aialenti / r2.py

Last active February 12, 2020 21:28

	from sklearn.metrics import r2_score

	def xgb_r2_score(preds, dtrain):
	labels = dtrain.get_label()
	return 'r2', r2_score(labels, preds)

aialenti / grid search.py

Last active February 2, 2020 18:44

	# Imports
	import numpy as np
	import pandas as pd
	import xgboost as xgb
	from interruptingcow import timeout
	from sklearn.model_selection import KFold # import KFold
	from sklearn.metrics import r2_score
	import json
	from preprocessing import preprocessing, xgb_r2_score # The preprocessing and the r2 evaluation
	from generate_grid import get_grid_iterable # The grid