shengch02’s gists

shengch02 / Mbenz Kaggle solution 3

Created July 19, 2017 01:44

outliers

	#utilizing one-hot-encoding, Randomforest, and xgboost to predict the outliers
	import numpy as np
	from sklearn.base import BaseEstimator,TransformerMixin, ClassifierMixin
	from sklearn.preprocessing import LabelEncoder
	import xgboost as xgb
	import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
	from sklearn.ensemble import GradientBoostingClassifier
	import time
	from sklearn.model_selection import KFold
	from sklearn.ensemble import RandomForestClassifier

shengch02 / Mbenz Kaggle solution 2

Created July 19, 2017 01:43

XGB + Pipeline

	import numpy as np
	import pandas as pd
	import matplotlib.pyplot as plt
	#import seaborn as sns
	#matplotlib inline
	from sklearn import model_selection, preprocessing
	import xgboost as xgb
	import datetime
	import operator
	from sklearn.cross_validation import train_test_split

shengch02 / Mbenz Kaggle solution 1

Created July 19, 2017 01:42

XGB

	import pandas as pd
	import numpy as np
	from sklearn.linear_model import LogisticRegression
	from sklearn.linear_model import LinearRegression
	from sklearn.feature_selection import RFE
	from sklearn.cross_validation import cross_val_score, train_test_split
	import xgboost as xgb
	from sklearn.metrics import r2_score

shengch02 / Mbenz Kaggle solution 0

Created July 19, 2017 01:40

Linear Model

	import pandas as pd
	import numpy as np
	from sklearn.linear_model import LogisticRegression
	from sklearn.linear_model import LinearRegression
	from sklearn.feature_selection import RFE
	from sklearn.cross_validation import cross_val_score, train_test_split

	#input the data
	data0 = pd.read_csv('./data/train.csv', sep=',', header=False, names=range(378))
	data = data0

shengch02 / Bosch Kaggle competition solution

Last active July 19, 2017 01:46

	import pandas as pd
	import numpy as np
	import matplotlib.pyplot as plt
	from collections import Counter
	from sklearn.model_selection import KFold
	from sklearn.ensemble import RandomForestClassifier
	import xgboost as xgb
	from sklearn.metrics import matthews_corrcoef as mc
	import operator

shengch02 / Stochastic gradient ascent

Created January 5, 2017 02:06

(Python) Implement stochastic gradient ascent with L2 penalty. Compare convergence of stochastic gradient ascent with that of batch gradient ascent.

	#Training logistic regression via stochastic gradient ascent
	import math
	import pandas as pd
	import numpy as np

	#the dataset consists a subset of baby product reviews on Amazon.com
	import sframe
	products = sframe.SFrame('amazon_baby_subset.gl/')
	products = sframe.SFrame.to_dataframe(products)

shengch02 / Explore precision and recall

Created January 3, 2017 17:59

(Python) Explore various evaluation metrics: accuracy, confusion matrix, precision, recall. Explore how various metrics can be combined to produce a cost of making an error. Explore precision and recall curves.

	#explore precision and recall
	import pandas as pd
	import numpy as np

	#the dataset consists of baby product reviews on Amazon.com
	import sframe
	products = sframe.SFrame('amazon_baby.gl/')

	#clean the original data: remove punctuation, fill in N/A, remove neutral sentiment,
	# perform a train/test split, produce word count matrix

shengch02 / Implementing gradient boosted trees from scratch

Created January 2, 2017 17:08

(Python) Train a boosted ensemble of decision-trees (gradient boosted trees) on the lending club dataset. Predict whether a loan will default along with prediction probabilities. Evaluate the trained model and compare it with a baseline.

	#Boosting a decision stump from scratch
	import pandas as pd
	import numpy as np

	#the dataset consists data from the LendingClub to predict whether a loan will be paid off in full or
	#the loan with be charged off and possibly go into default
	import sframe
	loans = sframe.SFrame('lending-club-data.gl/')

	#target column 'safe_loans' with +1 means a safe loan and -1 for risky loan

shengch02 / Gradient boosted trees

Created January 2, 2017 01:29

(Python) Train a boosted ensemble of decision-trees (gradient boosted trees) on the lending club dataset. Predict whether a loan will default along with prediction probabilities (on a validation set). Find the most positive and negative loans using the learned model. Explore how the number of trees influences classification performance.

	#use the pre-implemented gradient boosted trees
	import pandas as pd
	import numpy as np

	#the dataset consists data from the LendingClub to predict whether a loan will be paid off in full or
	#the loan with be charged off and possibly go into default
	import sframe
	loans = sframe.SFrame('lending-club-data.gl/')

	#target column 'safe_loans' with +1 means a safe loan and -1 for risky loan

shengch02 / explore various techniques for preventing overfitting in decision trees

Created December 28, 2016 22:00

(Python) Implement binary decision trees with different early stopping methods. Compare models with different stopping parameters.

	#explore various techniques for preventing overfitting in decision trees
	import math
	import pandas as pd
	import numpy as np

	#the dataset consists data from the LendingClub to predict whether a loan will be paid off in full or
	#the loan with be charged off and possibly go into default
	import sframe
	loans = sframe.SFrame('lending-club-data.gl/')