algorithm/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2025-07-05 17:34:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add pep8-naming to pre-commit hooks and fixes incorrect naming conventions (#7062)

Browse Source 
* ci(pre-commit): Add pep8-naming to `pre-commit` hooks (#7038)

* refactor: Fix naming conventions (#7038)

* Update arithmetic_analysis/lu_decomposition.py

Co-authored-by: Christian Clauss <cclauss@me.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* refactor(lu_decomposition): Replace `NDArray` with `ArrayLike` (#7038)

* chore: Fix naming conventions in doctests (#7038)

* fix: Temporarily disable project euler problem 104 (#7069)

* chore: Fix naming conventions in doctests (#7038)

Co-authored-by: Christian Clauss <cclauss@me.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Caeden
2022-10-12 23:54:20 +01:00
committed by GitHub
parent e2cd982b11
commit 07e991d553
140 changed files with 1552 additions and 1536 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
machine_learning/k_means_clust.py
View File

@ -69,8 +69,8 @@ def get_initial_centroids(data, k, seed=None):
return centroids
def centroid_pairwise_dist(X, centroids):
return pairwise_distances(X, centroids, metric="euclidean")
def centroid_pairwise_dist(x, centroids):
return pairwise_distances(x, centroids, metric="euclidean")
def assign_clusters(data, centroids):
@ -197,8 +197,8 @@ if False: # change to true to run this test case.
plot_heterogeneity(heterogeneity, k)
def ReportGenerator(
df: pd.DataFrame, ClusteringVariables: np.ndarray, FillMissingReport=None
def report_generator(
df: pd.DataFrame, clustering_variables: np.ndarray, fill_missing_report=None
) -> pd.DataFrame:
"""
Function generates easy-erading clustering report. It takes 2 arguments as an input:
@ -214,7 +214,7 @@ def ReportGenerator(
>>> data['col2'] = [100, 200, 300]
>>> data['col3'] = [10, 20, 30]
>>> data['Cluster'] = [1, 1, 2]
>>> ReportGenerator(data, ['col1', 'col2'], 0)
>>> report_generator(data, ['col1', 'col2'], 0)
Features Type Mark 1 2
0 # of Customers ClusterSize False 2.000000 1.000000
1 % of Customers ClusterProportion False 0.666667 0.333333
@ -231,8 +231,8 @@ def ReportGenerator(
[104 rows x 5 columns]
"""
# Fill missing values with given rules
if FillMissingReport:
df.fillna(value=FillMissingReport, inplace=True)
if fill_missing_report:
df.fillna(value=fill_missing_report, inplace=True)
df["dummy"] = 1
numeric_cols = df.select_dtypes(np.number).columns
report = (
@ -313,7 +313,7 @@ def ReportGenerator(
report = pd.concat(
[report, a, clustersize, clusterproportion], axis=0
) # concat report with clustert size and nan values
report["Mark"] = report["Features"].isin(ClusteringVariables)
report["Mark"] = report["Features"].isin(clustering_variables)
cols = report.columns.tolist()
cols = cols[0:2] + cols[-1:] + cols[2:-1]
report = report[cols]