statslibx 0.1.6__py3-none-any.whl → 0.1.8__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- statslibx/__init__.py +15 -8
- statslibx/cli.py +47 -0
- statslibx/computacional.py +2 -0
- statslibx/datasets/__init__.py +236 -8
- statslibx/descriptive.py +502 -160
- statslibx/inferential.py +746 -307
- statslibx/io.py +21 -0
- statslibx/preprocessing/__init__.py +228 -0
- statslibx/probability.py +2 -0
- statslibx/utils.py +112 -150
- {statslibx-0.1.6.dist-info → statslibx-0.1.8.dist-info}/METADATA +27 -32
- statslibx-0.1.8.dist-info/RECORD +15 -0
- statslibx-0.1.8.dist-info/entry_points.txt +2 -0
- statslibx/datasets/course_completion.csv +0 -100001
- statslibx/datasets/iris.csv +0 -151
- statslibx/datasets/penguins.csv +0 -345
- statslibx/datasets/sp500_companies.csv +0 -504
- statslibx/datasets/titanic.csv +0 -419
- statslibx-0.1.6.dist-info/RECORD +0 -14
- {statslibx-0.1.6.dist-info → statslibx-0.1.8.dist-info}/WHEEL +0 -0
- {statslibx-0.1.6.dist-info → statslibx-0.1.8.dist-info}/top_level.txt +0 -0
statslibx/__init__.py
CHANGED
|
@@ -1,28 +1,32 @@
|
|
|
1
1
|
"""
|
|
2
2
|
StatsLibx - Librería de Estadística para Python
|
|
3
3
|
Autor: Emmanuel Ascendra
|
|
4
|
-
Versión: 0.1.
|
|
4
|
+
Versión: 0.1.8
|
|
5
5
|
"""
|
|
6
6
|
|
|
7
|
-
__version__ = "0.1.
|
|
7
|
+
__version__ = "0.1.8"
|
|
8
8
|
__author__ = "Emmanuel Ascendra"
|
|
9
9
|
|
|
10
10
|
# Importar las clases principales
|
|
11
11
|
from .descriptive import DescriptiveStats, DescriptiveSummary
|
|
12
12
|
from .inferential import InferentialStats, TestResult
|
|
13
|
+
from .probability import ProbabilityStats
|
|
14
|
+
from .computacional import ComputacionalStats
|
|
13
15
|
from .utils import UtilsStats
|
|
14
|
-
from .
|
|
16
|
+
from .preprocessing import Preprocessing
|
|
17
|
+
from .datasets import load_dataset, generate_dataset
|
|
15
18
|
|
|
16
19
|
# Definir qué se expone cuando se hace: from statslib import *
|
|
17
20
|
__all__ = [
|
|
18
21
|
# Clases principales
|
|
19
22
|
'DescriptiveStats',
|
|
20
|
-
'InferentialStats',
|
|
21
|
-
'
|
|
22
|
-
'
|
|
23
|
-
'TestResult',
|
|
23
|
+
'InferentialStats',
|
|
24
|
+
'ProbabilityStats',
|
|
25
|
+
'ComputacionalStats',
|
|
24
26
|
'UtilsStats',
|
|
25
|
-
'
|
|
27
|
+
'Preprocessing',
|
|
28
|
+
'load_dataset',
|
|
29
|
+
'generate_dataset'
|
|
26
30
|
]
|
|
27
31
|
|
|
28
32
|
# Mensaje de bienvenida (opcional)
|
|
@@ -35,4 +39,7 @@ def welcome():
|
|
|
35
39
|
print(f" - DescriptiveStats: Estadística descriptiva")
|
|
36
40
|
print(f" - InferentialStats: Estadística inferencial")
|
|
37
41
|
print(f" - UtilsStats: Utilidades Extras")
|
|
42
|
+
print(f"\nMódulos disponibles:")
|
|
43
|
+
print(f" - Datasets: Carga de Datasets")
|
|
44
|
+
print(f" - Preprocessing: Preprocesamiento de datos")
|
|
38
45
|
print(f"\nPara más información: help(statslibx)")
|
statslibx/cli.py
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
import argparse
|
|
2
|
+
from statslibx.io import load_file
|
|
3
|
+
from statslibx.preprocessing import Preprocessing
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
def main():
|
|
7
|
+
parser = argparse.ArgumentParser(
|
|
8
|
+
prog="statslibx",
|
|
9
|
+
description="Statslibx - Data analysis from terminal"
|
|
10
|
+
)
|
|
11
|
+
|
|
12
|
+
subparsers = parser.add_subparsers(dest="command")
|
|
13
|
+
|
|
14
|
+
# describe
|
|
15
|
+
describe = subparsers.add_parser("describe")
|
|
16
|
+
describe.add_argument("file")
|
|
17
|
+
|
|
18
|
+
# quality
|
|
19
|
+
quality = subparsers.add_parser("quality")
|
|
20
|
+
quality.add_argument("file")
|
|
21
|
+
|
|
22
|
+
# preview
|
|
23
|
+
preview = subparsers.add_parser("preview")
|
|
24
|
+
preview.add_argument("file")
|
|
25
|
+
preview.add_argument("-n", "--rows", type=int, default=5)
|
|
26
|
+
|
|
27
|
+
args = parser.parse_args()
|
|
28
|
+
|
|
29
|
+
if not args.command:
|
|
30
|
+
parser.print_help()
|
|
31
|
+
return
|
|
32
|
+
|
|
33
|
+
df = load_file(args.file)
|
|
34
|
+
pp = Preprocessing(df)
|
|
35
|
+
|
|
36
|
+
if args.command == "describe":
|
|
37
|
+
print(pp.describe_numeric())
|
|
38
|
+
|
|
39
|
+
elif args.command == "quality":
|
|
40
|
+
print(pp.data_quality())
|
|
41
|
+
|
|
42
|
+
elif args.command == "preview":
|
|
43
|
+
print(pp.preview_data(args.rows))
|
|
44
|
+
|
|
45
|
+
|
|
46
|
+
if __name__ == "__main__":
|
|
47
|
+
main()
|
statslibx/datasets/__init__.py
CHANGED
|
@@ -1,16 +1,244 @@
|
|
|
1
|
-
import
|
|
2
|
-
import pkgutil
|
|
1
|
+
from typing import Optional, Union, Literal, List, Tuple
|
|
3
2
|
import io
|
|
3
|
+
import pkgutil
|
|
4
|
+
|
|
5
|
+
import pandas as pd
|
|
6
|
+
import polars as pl
|
|
7
|
+
import numpy as np
|
|
8
|
+
from numpy.typing import NDArray
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
_SUPPORTED_BACKENDS = ("pandas", "polars")
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
def _validate_columns(
|
|
15
|
+
df: Union[pd.DataFrame, pl.DataFrame],
|
|
16
|
+
X_columns: List[str],
|
|
17
|
+
y_column: str
|
|
18
|
+
) -> None:
|
|
19
|
+
columns = set(df.columns)
|
|
20
|
+
missing = set(X_columns + [y_column]) - columns
|
|
21
|
+
if missing:
|
|
22
|
+
raise ValueError(f"Columnas no encontradas en el dataset: {missing}")
|
|
23
|
+
|
|
24
|
+
|
|
25
|
+
def _X_y(
|
|
26
|
+
df: Union[pd.DataFrame, pl.DataFrame],
|
|
27
|
+
X_columns: List[str],
|
|
28
|
+
y_column: str
|
|
29
|
+
) -> Tuple[NDArray, NDArray]:
|
|
30
|
+
"""
|
|
31
|
+
Extrae X e y como arrays numpy desde pandas o polars.
|
|
32
|
+
"""
|
|
33
|
+
_validate_columns(df, X_columns, y_column)
|
|
4
34
|
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
35
|
+
if isinstance(df, pd.DataFrame):
|
|
36
|
+
X = df[X_columns].to_numpy()
|
|
37
|
+
y = df[y_column].to_numpy().ravel()
|
|
38
|
+
return X, y
|
|
39
|
+
|
|
40
|
+
elif isinstance(df, pl.DataFrame):
|
|
41
|
+
X = df.select(X_columns).to_numpy()
|
|
42
|
+
y = df.select(y_column).to_numpy().ravel()
|
|
43
|
+
return X, y
|
|
44
|
+
|
|
45
|
+
else:
|
|
46
|
+
raise TypeError(
|
|
47
|
+
"Backend no soportado. Use pandas.DataFrame o polars.DataFrame."
|
|
48
|
+
)
|
|
49
|
+
|
|
50
|
+
|
|
51
|
+
def load_dataset(
|
|
52
|
+
name: str,
|
|
53
|
+
backend: Literal["pandas", "polars"] = "pandas",
|
|
54
|
+
return_X_y: Optional[Tuple[List[str], str]] = None
|
|
55
|
+
) -> Union[pd.DataFrame, pl.DataFrame, Tuple[NDArray, NDArray]]:
|
|
56
|
+
"""
|
|
57
|
+
Carga un dataset interno del paquete.
|
|
58
|
+
|
|
59
|
+
Datasets disponibles:
|
|
8
60
|
- iris.csv
|
|
9
61
|
- penguins.csv
|
|
10
62
|
- sp500_companies.csv
|
|
11
63
|
- titanic.csv
|
|
64
|
+
- course_completion.csv
|
|
65
|
+
|
|
66
|
+
Parámetros
|
|
67
|
+
----------
|
|
68
|
+
name : str
|
|
69
|
+
Nombre del archivo CSV.
|
|
70
|
+
backend : {'pandas', 'polars'}, default='pandas'
|
|
71
|
+
Backend de DataFrame a utilizar.
|
|
72
|
+
return_X_y : tuple[list[str], str], optional
|
|
73
|
+
Si se especifica, devuelve (X, y) como arrays numpy,
|
|
74
|
+
|
|
75
|
+
Retorna
|
|
76
|
+
-------
|
|
77
|
+
DataFrame o (X, y)
|
|
12
78
|
"""
|
|
79
|
+
if backend not in _SUPPORTED_BACKENDS:
|
|
80
|
+
raise ValueError(
|
|
81
|
+
f"Backend '{backend}' no soportado. "
|
|
82
|
+
f"Use uno de {_SUPPORTED_BACKENDS}."
|
|
83
|
+
)
|
|
84
|
+
|
|
85
|
+
# ---------- 1️⃣ Intentar cargar desde el paquete ----------
|
|
13
86
|
data_bytes = pkgutil.get_data("statslibx.datasets", name)
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
|
|
87
|
+
|
|
88
|
+
if data_bytes is not None:
|
|
89
|
+
df = (
|
|
90
|
+
pd.read_csv(io.BytesIO(data_bytes))
|
|
91
|
+
if backend == "pandas"
|
|
92
|
+
else pl.read_csv(io.BytesIO(data_bytes))
|
|
93
|
+
)
|
|
94
|
+
|
|
95
|
+
# ---------- 2️⃣ Si no está en el paquete, buscar en ruta actual ----------
|
|
96
|
+
else:
|
|
97
|
+
try:
|
|
98
|
+
df = (
|
|
99
|
+
pd.read_csv(name)
|
|
100
|
+
if backend == "pandas"
|
|
101
|
+
else pl.read_csv(name)
|
|
102
|
+
)
|
|
103
|
+
except FileNotFoundError:
|
|
104
|
+
raise FileNotFoundError(
|
|
105
|
+
f"Dataset '{name}' no encontrado "
|
|
106
|
+
f"ni en statslibx.datasets ni en la ruta actual."
|
|
107
|
+
)
|
|
108
|
+
|
|
109
|
+
# ---------- 3️⃣ Devolver X, y si se solicita ----------
|
|
110
|
+
if return_X_y is not None:
|
|
111
|
+
X_columns, y_column = return_X_y
|
|
112
|
+
return _X_y(df, X_columns, y_column)
|
|
113
|
+
|
|
114
|
+
return df
|
|
115
|
+
|
|
116
|
+
# =========================
|
|
117
|
+
# Datasets específicos
|
|
118
|
+
# =========================
|
|
119
|
+
|
|
120
|
+
def load_iris(
|
|
121
|
+
backend: Literal["pandas", "polars"] = "pandas",
|
|
122
|
+
return_X_y: Optional[Tuple[List[str], str]] = None
|
|
123
|
+
):
|
|
124
|
+
return load_dataset(
|
|
125
|
+
"iris.csv",
|
|
126
|
+
backend=backend,
|
|
127
|
+
return_X_y=return_X_y
|
|
128
|
+
)
|
|
129
|
+
|
|
130
|
+
|
|
131
|
+
def load_penguins(
|
|
132
|
+
backend: Literal["pandas", "polars"] = "pandas",
|
|
133
|
+
return_X_y: Optional[Tuple[List[str], str]] = None
|
|
134
|
+
):
|
|
135
|
+
return load_dataset(
|
|
136
|
+
"penguins.csv",
|
|
137
|
+
backend=backend,
|
|
138
|
+
return_X_y=return_X_y
|
|
139
|
+
)
|
|
140
|
+
|
|
141
|
+
|
|
142
|
+
from typing import Optional
|
|
143
|
+
|
|
144
|
+
def generate_dataset(n_rows, schema, seed=None, save: Optional[bool] = False, filename: Optional[str] = None):
|
|
145
|
+
if seed is not None:
|
|
146
|
+
if not isinstance(seed, int):
|
|
147
|
+
raise TypeError("seed debe ser un entero o None")
|
|
148
|
+
np.random.seed(seed)
|
|
149
|
+
else:
|
|
150
|
+
np.random.seed(42)
|
|
151
|
+
|
|
152
|
+
if not isinstance(schema, dict):
|
|
153
|
+
raise TypeError("schema debe ser un diccionario")
|
|
154
|
+
|
|
155
|
+
|
|
156
|
+
|
|
157
|
+
data = {}
|
|
158
|
+
|
|
159
|
+
for col, config in schema.items():
|
|
160
|
+
if "dist" not in config:
|
|
161
|
+
raise ValueError(f"La columna '{col}' no tiene 'dist' definido")
|
|
162
|
+
|
|
163
|
+
dist = config["dist"]
|
|
164
|
+
dtype = config.get("type", "float")
|
|
165
|
+
nround = config.get("round", 0)
|
|
166
|
+
|
|
167
|
+
# ---------- DISTRIBUCIONES ----------
|
|
168
|
+
if dist == "normal":
|
|
169
|
+
values = np.random.normal(
|
|
170
|
+
loc=config.get("mean", 0),
|
|
171
|
+
scale=config.get("std", 1),
|
|
172
|
+
size=n_rows
|
|
173
|
+
)
|
|
174
|
+
|
|
175
|
+
elif dist == "uniform":
|
|
176
|
+
values = np.random.uniform(
|
|
177
|
+
low=config.get("low", 0),
|
|
178
|
+
high=config.get("high", 1),
|
|
179
|
+
size=n_rows
|
|
180
|
+
)
|
|
181
|
+
|
|
182
|
+
elif dist == "exponential":
|
|
183
|
+
values = np.random.exponential(
|
|
184
|
+
scale=config.get("scale", 1),
|
|
185
|
+
size=n_rows
|
|
186
|
+
)
|
|
187
|
+
|
|
188
|
+
elif dist == "lognormal":
|
|
189
|
+
values = np.random.lognormal(
|
|
190
|
+
mean=config.get("mean", 0),
|
|
191
|
+
sigma=config.get("std", 1),
|
|
192
|
+
size=n_rows
|
|
193
|
+
)
|
|
194
|
+
|
|
195
|
+
elif dist == "poisson":
|
|
196
|
+
values = np.random.poisson(
|
|
197
|
+
lam=config.get("lam", 1),
|
|
198
|
+
size=n_rows
|
|
199
|
+
)
|
|
200
|
+
|
|
201
|
+
elif dist == "binomial":
|
|
202
|
+
values = np.random.binomial(
|
|
203
|
+
n=config.get("n", 1),
|
|
204
|
+
p=config.get("p", 0.5),
|
|
205
|
+
size=n_rows
|
|
206
|
+
)
|
|
207
|
+
|
|
208
|
+
elif dist == "categorical":
|
|
209
|
+
if "choices" not in config:
|
|
210
|
+
raise ValueError(f"'choices' es requerido para categorical ({col})")
|
|
211
|
+
values = np.random.choice(
|
|
212
|
+
config["choices"],
|
|
213
|
+
size=n_rows
|
|
214
|
+
)
|
|
215
|
+
data[col] = values
|
|
216
|
+
continue
|
|
217
|
+
|
|
218
|
+
else:
|
|
219
|
+
raise ValueError(f"Distribución no soportada: {dist}")
|
|
220
|
+
|
|
221
|
+
# ---------- CASTEO DE TIPO ----------
|
|
222
|
+
if dtype == "int":
|
|
223
|
+
values = np.round(values).astype(int)
|
|
224
|
+
elif dtype == "float":
|
|
225
|
+
values = values.astype(float)
|
|
226
|
+
else:
|
|
227
|
+
raise ValueError(f"Tipo no soportado: {dtype}")
|
|
228
|
+
|
|
229
|
+
# ---------- REDONDEO ----------
|
|
230
|
+
if nround > 0:
|
|
231
|
+
values = np.round(values, nround)
|
|
232
|
+
else:
|
|
233
|
+
values = np.round(values, 2)
|
|
234
|
+
|
|
235
|
+
data[col] = values
|
|
236
|
+
|
|
237
|
+
if save and filename:
|
|
238
|
+
df = pd.DataFrame(data)
|
|
239
|
+
df.to_csv(f"{filename}.csv", index=False)
|
|
240
|
+
else:
|
|
241
|
+
df = pd.DataFrame(data)
|
|
242
|
+
df.to_csv("dataset.csv", index=False)
|
|
243
|
+
|
|
244
|
+
return pd.DataFrame(data)
|