def boston_housing_data():
"""Boston Housing dataset.
Source : https://archive.ics.uci.edu/ml/datasets/Housing
Number of samples : 506
Continuous target variable : MEDV
MEDV = Median value of owner-occupied homes in $1000's
Dataset Attributes:
- 1) CRIM per capita crime rate by town
- 2) ZN proportion of residential land zoned for lots over
25,000 sq.ft.
- 3) INDUS proportion of non-retail business acres per town
- 4) CHAS Charles River dummy variable (= 1 if tract bounds
river; 0 otherwise)
- 5) NOX nitric oxides concentration (parts per 10 million)
- 6) RM average number of rooms per dwelling
- 7) AGE proportion of owner-occupied units built prior to 1940
- 8) DIS weighted distances to five Boston employment centres
- 9) RAD index of accessibility to radial highways
- 10) TAX full-value property-tax rate per $10,000
- 11) PTRATIO pupil-teacher ratio by town
- 12) B 1000(Bk - 0.63)^2 where Bk is the prop. of b. by town
- 13) LSTAT % lower status of the population
Returns
--------
X, y : [n_samples, n_features], [n_class_labels]
X is the feature matrix with 506 housing samples as rows
and 13 feature columns.
y is a 1-dimensional array of the continuous target variable MEDV
Examples
-----------
For usage examples, please see
http://rasbt.github.io/mlxtend/user_guide/data/boston_housing_data/
"""
data = read_csv(filename2path("boston-housing.csv"), index_col=0)
return df2Xy(data, 'medv')
def kaggle_gmsc_data_nomissing():
data = read_csv(filename2path("give-me-some-credit"), index_col=0)
data.dropna(inplace=True)
return df2Xy(data, 'SeriousDlqin2yrs')
# du -h train_full_raw.csv
# wc -l train_full_raw.csv
# ```
# + [markdown] slideshow={"slide_type": "slide"}
# We'll go through this data by "chunks". Let's set the size of a chunk (can be accessed by papermill):
# + tags=["parameters"]
CHUNK_SIZE = 1000 # small value for fast execution; can bump to 10000
# -
# Let's create a chunk "reader":
from mlxtend.utils.data import filename2path
from pandas import read_csv
TRAIN_FILE = filename2path("avazu")
HEADER = ['id','click','hour','C1','banner_pos','site_id','site_domain','site_category','app_id','app_domain','app_category','device_id'\
,'device_ip','device_model','device_type','device_conn_type','C14','C15','C16','C17','C18','C19','C20','C21']
reader = read_csv(TRAIN_FILE,
chunksize=CHUNK_SIZE,
names=HEADER,
header=0,
index_col=0)
reader
# + [markdown] slideshow={"slide_type": "slide"}
# There are about 4,000 chunks of size 10,000 in this data.
#
# Let's look at the first chunk:
# -
def kaggle_house_prices():
data = read_csv(filename2path("house-prices"), index_col=0)
data.dropna(inplace=True)
return df2Xy(data)
def hotel_reviews_data():
data = read_csv(filename2path("hotel-reviews.csv"))
X = data.text.values
y = data.label.values
return X, y