klib.utils._corr_selector() - Code Metrics - Inspection of "Resolving pre-commit-hook changes" - akanz1/klib - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( c20d75...406f67 )

by Andreas

created 2020-07-24 15:30 UTC

klib.utils._corr_selector() B

↳ Parent: klib.utils

Complexity

Conditions

Size

Total Lines	43
Code Lines	21

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	5
eloc	21
nop	3
dl	0
loc	43
rs	8.9093
c	0
b	0
f	0

"""
Utilities and auxiliary functions.

:author: Andreas Kanz

"""

# Imports
import numpy as np
import pandas as pd
from typing import Any, Dict, List, Optional, Tuple, Union


def _corr_selector(
    corr: Union[pd.Series, pd.DataFrame],
    split: Optional[
        str
    ] = None,  # Optional[Literal["pos", "neg", "above", "below"]] = None,
    threshold: float = 0,
) -> Union[pd.Series, pd.DataFrame]:
    """[summary]

    Parameters
    ----------
    corr : Union[pd.Series, pd.DataFrame]
        pd.Series or pd.DataFrame of correlations
    split : Optional[str], optional
        Type of split performed, by default None
           * {None, 'pos', 'neg', 'above', 'below'}
    threshold : float, optional
        Value between 0 and 1 to set the correlation threshold, by default 0

    Returns
    -------
    pd.DataFrame
        List or matrix of (filtered) correlations
    """

    if split == "pos":
        corr = corr.where((corr >= threshold) & (corr > 0))
        print(
            'Displaying positive correlations. Use "threshold" to further limit the results.'
        )
    elif split == "neg":
        corr = corr.where((corr <= threshold) & (corr < 0))
        print(
            'Displaying negative correlations. Use "threshold" to further limit the results.'
        )
    elif split == "above":
        corr = corr.where(np.abs(corr) >= threshold)
        print(f"Displaying absolute correlations above the threshold ({threshold}).")
    elif split == "below":
        corr = corr.where(np.abs(corr) <= threshold)
        print(f"Displaying absolute correlations below the threshold ({threshold}).")

    return corr


def _diff_report(
    data: pd.DataFrame,
    data_cleaned: pd.DataFrame,
    dupl_rows: Optional[List[Union[str, int]]] = None,
    single_val_cols: Optional[List[str]] = None,
    show: Optional[str] = "changes",  # Optional[Literal["all", "changes"]] = "changes",
) -> None:
    """ Provides information about changes between two datasets, such as dropped rows and columns, memory usage and \
    missing values.

    Parameters
    ----------
    data : pd.DataFrame
        2D dataset that can be coerced into Pandas DataFrame. Input the initial dataset here
    data_cleaned : pd.DataFrame
        2D dataset that can be coerced into Pandas DataFrame. Input the cleaned / updated dataset here
    dupl_rows : Optional[List[Union[str, int]]], optional
        List of duplicate row indices, by default None
    single_val_cols : Optional[List[str]], optional
        List of single-valued column indices. I.e. columns where all cells contain the same value. \
        NaNs count as a separate value, by default None
    show : str, optional
        {'all', 'changes', None}, by default "changes"
        Specify verbosity of the output:
            * 'all': Print information about the data before and after cleaning as well as information about changes \
            and memory usage (deep). Please be aware, that this can slow down the function by quite a bit.
            * 'changes': Print out differences in the data before and after cleaning.
            * None: No information about the data and the data cleaning is printed.

    Returns
    -------
    None
        Print statement highlighting the datasets or changes between the two datasets.
    """

    if show in ["changes", "all"]:
        dupl_rows = [] if dupl_rows is None else dupl_rows.copy()
        single_val_cols = [] if single_val_cols is None else single_val_cols.copy()
        data_mem = _memory_usage(data, deep=False)
        data_cl_mem = _memory_usage(data_cleaned, deep=False)
        data_mv_tot = _missing_vals(data)["mv_total"]
        data_cl_mv_tot = _missing_vals(data_cleaned)["mv_total"]

        if show == "all":
            data_mem = _memory_usage(data, deep=True)
            data_cl_mem = _memory_usage(data_cleaned, deep=True)
            print("Before data cleaning:\n")
            print(f"dtypes:\n{data.dtypes.value_counts()}")
            print(f"\nNumber of rows: {data.shape[0]}")
            print(f"Number of cols: {data.shape[1]}")
            print(f"Missing values: {data_mv_tot}")
            print(f"Memory usage: {data_mem} MB")
            print("_______________________________________________________\n")
            print("After data cleaning:\n")
            print(f"dtypes:\n{data_cleaned.dtypes.value_counts()}")
            print(f"\nNumber of rows: {data_cleaned.shape[0]}")
            print(f"Number of cols: {data_cleaned.shape[1]}")
            print(f"Missing values: {data_cl_mv_tot}")
            print(f"Memory usage: {data_cl_mem} MB")
            print("_______________________________________________________\n")

        print(
            f"Shape of cleaned data: {data_cleaned.shape} - Remaining NAs: {data_cl_mv_tot}"
        )
        print(f"\nChanges:")
        print(f"Dropped rows: {data.shape[0]-data_cleaned.shape[0]}")
        print(f"     of which {len(dupl_rows)} duplicates. (Rows: {dupl_rows})")
        print(f"Dropped columns: {data.shape[1]-data_cleaned.shape[1]}")
        print(
            f"     of which {len(single_val_cols)} single valued. (Columns: {single_val_cols})"
        )
        print(f"Dropped missing values: {data_mv_tot-data_cl_mv_tot}")
        mem_change = data_mem - data_cl_mem
        print(
            f"Reduced memory by at least: {round(mem_change,2)} MB (-{round(100*mem_change/data_mem,1)}%)"
        )


def _drop_duplicates(data: pd.DataFrame) -> Tuple[pd.DataFrame, Any]:
    """ Provides information on and drops duplicate rows.

    Parameters
    ----------
    data : pd.DataFrame
        2D dataset that can be coerced into Pandas DataFrame

    Returns
    -------
    Tuple[pd.DataFrame, List]
        Deduplicated Pandas DataFrame and Index Object of rows dropped
    """

    data = pd.DataFrame(data).copy()
    dupl_rows = data[data.duplicated()].index.tolist()
    data = data.drop(dupl_rows, axis="index")

    return data, dupl_rows


def _memory_usage(data: pd.DataFrame, deep: bool = True) -> float:
    """ Gives the total memory usage in megabytes.

    Parameters
    ----------
    data : pd.DataFrame
        2D dataset that can be coerced into Pandas DataFrame
    deep : bool, optional
        Runs a deep analysis of the memory usage, by default True

    Returns
    -------
    float
        Memory usage in megabytes
    """

    data = pd.DataFrame(data).copy()
    memory_usage = round(
        data.memory_usage(index=True, deep=deep).sum() / (1024 ** 2), 2
    )

    return memory_usage


def _missing_vals(data: pd.DataFrame) -> Dict[str, Any]:
    """ Gives metrics of missing values in the dataset.

    Parameters
    ----------
    data : pd.DataFrame
        2D dataset that can be coerced into Pandas DataFrame

    Returns
    -------
    Dict[str, float]
        mv_total: float, number of missing values in the entire dataset
        mv_rows: float, number of missing values in each row
        mv_cols: float, number of missing values in each column
        mv_rows_ratio: float, ratio of missing values for each row
        mv_cols_ratio: float, ratio of missing values for each column
    """

    data = pd.DataFrame(data).copy()
    mv_rows = data.isna().sum(axis=1)
    mv_cols = data.isna().sum(axis=0)
    mv_total = data.isna().sum().sum()
    mv_rows_ratio = mv_rows / data.shape[1]
    mv_cols_ratio = mv_cols / data.shape[0]

    return {
        "mv_total": mv_total,
        "mv_rows": mv_rows,
        "mv_cols": mv_cols,
        "mv_rows_ratio": mv_rows_ratio,
        "mv_cols_ratio": mv_cols_ratio,
    }


def _validate_input_bool(value, desc):
    if not (isinstance(value, bool)):
        raise TypeError(
            f"Input value for '{desc}' is {type(value)} but should be a boolean."
        )


def _validate_input_int(value, desc):
    if not isinstance(value, int):
        raise TypeError(
            f"Input value for '{desc}' is {type(value)} but should be an integer."
        )


def _validate_input_range(value, desc, lower, upper):
    if value < lower or value > upper:
        raise ValueError(
            f"'{desc}' = {value} but should be within the range {lower} <= '{desc}' <= {upper}."
        )


def _validate_input_smaller(value1, value2, desc):
    if value1 > value2:
        raise ValueError(
            f"The first input for '{desc}' should be smaller or equal to the second input."
        )


def _validate_input_sum(limit, desc, *args):
    if sum(args) > limit:
        raise ValueError(
            f"The sum of imput values provided for '{desc}' should be less or equal to {limit}."
        )


1			"""
2			Utilities and auxiliary functions.
3
4			:author: Andreas Kanz
5
6			"""
7
8			# Imports
9			import numpy as np
10			import pandas as pd
11			from typing import Any, Dict, List, Optional, Tuple, Union
12
13
14			def _corr_selector(
15			corr: Union[pd.Series, pd.DataFrame],
16			split: Optional[
17			str
18			] = None, # Optional[Literal["pos", "neg", "above", "below"]] = None,
19			threshold: float = 0,
20			) -> Union[pd.Series, pd.DataFrame]:
21			"""[summary]
22
23			Parameters
24			----------
25			corr : Union[pd.Series, pd.DataFrame]
26			pd.Series or pd.DataFrame of correlations
27			split : Optional[str], optional
28			Type of split performed, by default None
29			* {None, 'pos', 'neg', 'above', 'below'}
30			threshold : float, optional
31			Value between 0 and 1 to set the correlation threshold, by default 0
32
33			Returns
34			-------
35			pd.DataFrame
36			List or matrix of (filtered) correlations
37			"""
38
39			if split == "pos":
40			corr = corr.where((corr >= threshold) & (corr > 0))
41			print(
42			'Displaying positive correlations. Use "threshold" to further limit the results.'
43			)
44			elif split == "neg":
45			corr = corr.where((corr <= threshold) & (corr < 0))
46			print(
47			'Displaying negative correlations. Use "threshold" to further limit the results.'
48			)
49			elif split == "above":
50			corr = corr.where(np.abs(corr) >= threshold)
51			print(f"Displaying absolute correlations above the threshold ({threshold}).")
52			elif split == "below":
53			corr = corr.where(np.abs(corr) <= threshold)
54			print(f"Displaying absolute correlations below the threshold ({threshold}).")
55
56			return corr
57
58
59			def _diff_report(
60			data: pd.DataFrame,
61			data_cleaned: pd.DataFrame,
62			dupl_rows: Optional[List[Union[str, int]]] = None,
63			single_val_cols: Optional[List[str]] = None,
64			show: Optional[str] = "changes", # Optional[Literal["all", "changes"]] = "changes",
65			) -> None:
66			""" Provides information about changes between two datasets, such as dropped rows and columns, memory usage and \
67			missing values.
68
69			Parameters
70			----------
71			data : pd.DataFrame
72			2D dataset that can be coerced into Pandas DataFrame. Input the initial dataset here
73			data_cleaned : pd.DataFrame
74			2D dataset that can be coerced into Pandas DataFrame. Input the cleaned / updated dataset here
75			dupl_rows : Optional[List[Union[str, int]]], optional
76			List of duplicate row indices, by default None
77			single_val_cols : Optional[List[str]], optional
78			List of single-valued column indices. I.e. columns where all cells contain the same value. \
79			NaNs count as a separate value, by default None
80			show : str, optional
81			{'all', 'changes', None}, by default "changes"
82			Specify verbosity of the output:
83			* 'all': Print information about the data before and after cleaning as well as information about changes \
84			and memory usage (deep). Please be aware, that this can slow down the function by quite a bit.
85			* 'changes': Print out differences in the data before and after cleaning.
86			* None: No information about the data and the data cleaning is printed.
87
88			Returns
89			-------
90			None
91			Print statement highlighting the datasets or changes between the two datasets.
92			"""
93
94			if show in ["changes", "all"]:
95			dupl_rows = [] if dupl_rows is None else dupl_rows.copy()
96			single_val_cols = [] if single_val_cols is None else single_val_cols.copy()
97			data_mem = _memory_usage(data, deep=False)
98			data_cl_mem = _memory_usage(data_cleaned, deep=False)
99			data_mv_tot = _missing_vals(data)["mv_total"]
100			data_cl_mv_tot = _missing_vals(data_cleaned)["mv_total"]
101
102			if show == "all":
103			data_mem = _memory_usage(data, deep=True)
104			data_cl_mem = _memory_usage(data_cleaned, deep=True)
105			print("Before data cleaning:\n")
106			print(f"dtypes:\n{data.dtypes.value_counts()}")
107			print(f"\nNumber of rows: {data.shape[0]}")
108			print(f"Number of cols: {data.shape[1]}")
109			print(f"Missing values: {data_mv_tot}")
110			print(f"Memory usage: {data_mem} MB")
111			print("_______________________________________________________\n")
112			print("After data cleaning:\n")
113			print(f"dtypes:\n{data_cleaned.dtypes.value_counts()}")
114			print(f"\nNumber of rows: {data_cleaned.shape[0]}")
115			print(f"Number of cols: {data_cleaned.shape[1]}")
116			print(f"Missing values: {data_cl_mv_tot}")
117			print(f"Memory usage: {data_cl_mem} MB")
118			print("_______________________________________________________\n")
119
120			print(
121			f"Shape of cleaned data: {data_cleaned.shape} - Remaining NAs: {data_cl_mv_tot}"
122			)
123			print(f"\nChanges:")
124			print(f"Dropped rows: {data.shape[0]-data_cleaned.shape[0]}")
125			print(f" of which {len(dupl_rows)} duplicates. (Rows: {dupl_rows})")
126			print(f"Dropped columns: {data.shape[1]-data_cleaned.shape[1]}")
127			print(
128			f" of which {len(single_val_cols)} single valued. (Columns: {single_val_cols})"
129			)
130			print(f"Dropped missing values: {data_mv_tot-data_cl_mv_tot}")
131			mem_change = data_mem - data_cl_mem
132			print(
133			f"Reduced memory by at least: {round(mem_change,2)} MB (-{round(100*mem_change/data_mem,1)}%)"
134			)
135
136
137			def _drop_duplicates(data: pd.DataFrame) -> Tuple[pd.DataFrame, Any]:
138			""" Provides information on and drops duplicate rows.
139
140			Parameters
141			----------
142			data : pd.DataFrame
143			2D dataset that can be coerced into Pandas DataFrame
144
145			Returns
146			-------
147			Tuple[pd.DataFrame, List]
148			Deduplicated Pandas DataFrame and Index Object of rows dropped
149			"""
150
151			data = pd.DataFrame(data).copy()
152			dupl_rows = data[data.duplicated()].index.tolist()
153			data = data.drop(dupl_rows, axis="index")
154
155			return data, dupl_rows
156
157
158			def _memory_usage(data: pd.DataFrame, deep: bool = True) -> float:
159			""" Gives the total memory usage in megabytes.
160
161			Parameters
162			----------
163			data : pd.DataFrame
164			2D dataset that can be coerced into Pandas DataFrame
165			deep : bool, optional
166			Runs a deep analysis of the memory usage, by default True
167
168			Returns
169			-------
170			float
171			Memory usage in megabytes
172			"""
173
174			data = pd.DataFrame(data).copy()
175			memory_usage = round(
176			data.memory_usage(index=True, deep=deep).sum() / (1024 ** 2), 2
177			)
178
179			return memory_usage
180
181
182			def _missing_vals(data: pd.DataFrame) -> Dict[str, Any]:
183			""" Gives metrics of missing values in the dataset.
184
185			Parameters
186			----------
187			data : pd.DataFrame
188			2D dataset that can be coerced into Pandas DataFrame
189
190			Returns
191			-------
192			Dict[str, float]
193			mv_total: float, number of missing values in the entire dataset
194			mv_rows: float, number of missing values in each row
195			mv_cols: float, number of missing values in each column
196			mv_rows_ratio: float, ratio of missing values for each row
197			mv_cols_ratio: float, ratio of missing values for each column
198			"""
199
200			data = pd.DataFrame(data).copy()
201			mv_rows = data.isna().sum(axis=1)
202			mv_cols = data.isna().sum(axis=0)
203			mv_total = data.isna().sum().sum()
204			mv_rows_ratio = mv_rows / data.shape[1]
205			mv_cols_ratio = mv_cols / data.shape[0]
206
207			return {
208			"mv_total": mv_total,
209			"mv_rows": mv_rows,
210			"mv_cols": mv_cols,
211			"mv_rows_ratio": mv_rows_ratio,
212			"mv_cols_ratio": mv_cols_ratio,
213			}
214
215
216			def _validate_input_bool(value, desc):
217			if not (isinstance(value, bool)):
218			raise TypeError(
219			f"Input value for '{desc}' is {type(value)} but should be a boolean."
220			)
221
222
223			def _validate_input_int(value, desc):
224			if not isinstance(value, int):
225			raise TypeError(
226			f"Input value for '{desc}' is {type(value)} but should be an integer."
227			)
228
229
230			def _validate_input_range(value, desc, lower, upper):
231			if value < lower or value > upper:
232			raise ValueError(
233			f"'{desc}' = {value} but should be within the range {lower} <= '{desc}' <= {upper}."
234			)
235
236
237			def _validate_input_smaller(value1, value2, desc):
238			if value1 > value2:
239			raise ValueError(
240			f"The first input for '{desc}' should be smaller or equal to the second input."
241			)
242
243
244			def _validate_input_sum(limit, desc, *args):
245			if sum(args) > limit:
246			raise ValueError(
247			f"The sum of imput values provided for '{desc}' should be less or equal to {limit}."
248			)
249

akanz1 / klib

GitHub Access Token became invalid

Push — master ( c20d75...406f67 )

klib.utils._corr_selector() B

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like