BasedTab

Usage

Installation

Not on PyPI yet. Install:

git clone https://github.com/AnswerDotAI/basedtab.git
pip install -e .

How to use

Load data

read_csv and save_csv

from basedtab.core import BFrame

bf = BFrame.read_csv(toy_path)
bf.head(2)

["Number":[1 2]ₓ "City":["Dallas" "Dallas"] "Gender":["Male" "Male"] "Age":[41 54]ₓ "Income":[40367 45084] "Illness":["No" "No"]]

# Conversion to Pandas
df = bf.df 
df.head(2)

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; } .dataframe tbody tr th { vertical-align: top; } .dataframe thead th { text-align: right; } </style>

	Number	City	Gender	Age	Income	Illness
0	1	Dallas	Male	41	40367.0	No
1	2	Dallas	Male	54	45084.0	No

inc = bf["Income"]
inc.mean, inc.std, inc.skew, inc.kurt, inc.moment(5)

(Array(91252.79827333333),
 Array(24989.417649879582),
 Array(-0.3336387312149909),
 Array(3.5203677711666033),
 Array(-1.9377651398953264))

Groupby

from basedpl import add, tally, square
MEAN = add.reduce_first / tally
bf.groupby("City", "Income", mean=MEAN)

"Dallas"⌷
          Income
mean 45252.23119

"New York City"⌷
          Income
mean 96857.13139

"Los Angeles"⌷
          Income
mean 95264.15541

"Mountain View"⌷
          Income
mean 135078.4158

"Boston"⌷
         Income
mean 91554.5715

"Washington D.C."⌷
          Income
mean 70991.61281

"San Diego"⌷
          Income
mean 100756.2092

"Austin"⌷
          Income
mean 90277.51342

RMSE = MEAN.under(square)
bf.groupby("Gender", ["Age", "Income"], mean=MEAN, rmse=RMSE)

"Male"⌷
             Age      Income
mean  44.9126253  95670.2472
rmse 46.37557969 98752.06754

"Female"⌷
             Age      Income
mean 44.99776435 85660.92184
rmse 46.46704189 89097.22374

Rolling

ts = BFrame.read_csv(sp_path)
ts.head(2)

["index":[16606 16605]ₓ "date":["1950-01-03" "1950-01-04"] "open":[16.66 16.85] "high":[16.66 16.85] "low":[16.66 16.85] "close":[16.66 16.85] "volume":[1260000 1890000]ₓ "adj_close":[16.66 16.85]]

ts_df = ts.df
ts_df.head(2)

<style scoped> .dataframe tbody tr th:only-of-type { vertical-align: middle; } .dataframe tbody tr th { vertical-align: top; } .dataframe thead th { text-align: right; } </style>

	index	date	open	high	low	close	volume	adj_close
0	16606	1950-01-03	16.66	16.66	16.66	16.66	1260000	16.66
1	16605	1950-01-04	16.85	16.85	16.85	16.85	1890000	16.85

ts.rolling("close", size=3, edge="clamp", mean=MEAN)[:5]

0⌷
           close
mean 16.72333333

1⌷
           close
mean 16.81333333

2⌷
     close
mean 16.92

3⌷
           close
mean 16.99666667

4⌷
     close
mean 17.03

ts.rolling("close", size=2, step=2, mean=MEAN, rmse=RMSE)[:5]

0⌷
           close
mean      16.755
rmse 16.75526932

1⌷
           close
mean      16.955
rmse 16.95501843

2⌷
           close
mean      17.055
rmse 17.05501832

3⌷
           close
mean      16.925
rmse 16.92580426

4⌷
           close
mean      16.695
rmse 16.69501872

Plot

ts["close"].plot(title="Time Series")

bf["Income"].hist(title="Income Distribution")