From 7cb9508de184ec61c7859ba511dd9a9fa1355bfc Mon Sep 17 00:00:00 2001
From: sanyhe <sanyhew1097618435@163.com>
Date: Mon, 13 May 2024 13:30:39 +0800
Subject: [PATCH] fix: remove the step of formatting frotend code in CI, fix
the docs of clusteringexample and the selection of empty columns.
---
.pre-commit-config.yaml | 18 +++++++++---------
README.md | 4 ++--
.../Model Example/Clustering/Clustering.md | 2 +-
docs/source/Home/Introduction.md | 4 ++--
.../data_mining/data/data_readiness.py | 5 ++---
5 files changed, 16 insertions(+), 17 deletions(-)
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 19cd5666..da74e66c 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -58,15 +58,15 @@ repos:
args: [--config=.flake8]
exclude: ^node_modules/
- - repo: https://github.com/pre-commit/mirrors-prettier
- rev: v2.7.1
- hooks:
- - id: prettier
- name: Frontend Code Formatter
- description: Apply the Prettier code formatter
- files: \.(js|jsx|css|ts|tsx)$
- args: [--write, --semi=true, --single-quote=true, --trailing-comma=all, --print-width=200, --tab-width=4, --jsx-single-quote=false]
- exclude: ^node_modules/
+ # - repo: https://github.com/pre-commit/mirrors-prettier
+ # rev: v2.7.1
+ # hooks:
+ # - id: prettier
+ # name: Frontend Code Formatter
+ # description: Apply the Prettier code formatter
+ # files: \.(js|jsx|css|ts|tsx)$
+ # args: [--write, --semi=true, --single-quote=true, --trailing-comma=all, --print-width=200, --tab-width=4, --jsx-single-quote=false]
+ # exclude: ^node_modules/
# Problem: some dependencies cannot be installed with pre-commit
# - repo: https://github.com/pre-commit/mirrors-eslint
diff --git a/README.md b/README.md
index 2df57c6c..5916e887 100644
--- a/README.md
+++ b/README.md
@@ -306,13 +306,12 @@ The whole package is under construction and the documentation is progressively e
+ Mengying Ye (Mary, Jilin University, China)
+ Mengqi Gao (China University of Geosciences, Beijing, China)
+ Chengtu Li（Trenki, Henan Polytechnic University, Beijing, China）
++ Yucheng Yan (Andy, University of Sydney, Australia)
**Product Group**:
+ Yang Lyu (Daisy, Zhejiang University, China)
-+ Keran Li (Kirk, Chengdu University of Technology, China)
+ Bailun Jiang (EPSI / Lille University, France)
-+ Yucheng Yan (Andy, University of Sydney, Australia)
+ Ruitao Chang (China University of Geosciences Beijing, China)
+ Junchi Liao(Roceda, University of Electronic Science and Technology of China, China)
+ Panyan Weng (The University of Sydney, Australia)
@@ -388,6 +387,7 @@ More Videos will be recorded soon.
+ Qiuhao Zhao (Brad, Zhejiang University, China)
+ Kaixin Zheng (Hayne, Sun Yat-sen University, China)
+ Anzhou Li (Andrian, Zhejiang University, China)
++ Keran Li (Kirk, Chengdu University of Technology, China)
+ Dan Hu (Notre Dame University, United States)
+ Xunxin Liu (Tante, China University of Geosciences, Wuhan, China)
+ Fang Li (liv, Shenzhen University, China)
diff --git a/docs/source/For User/Model Example/Clustering/Clustering.md b/docs/source/For User/Model Example/Clustering/Clustering.md
index f946c5cb..65ca072c 100644
--- a/docs/source/For User/Model Example/Clustering/Clustering.md
+++ b/docs/source/For User/Model Example/Clustering/Clustering.md
@@ -3,7 +3,7 @@
Cluster analysis itself is not one specific algorithm, but the general task to be solved. It can be achieved by various algorithms that differ significantly in their understanding of what constitutes a cluster and how to efficiently find them. Popular notions of clusters include groups with small distances between cluster members, dense areas of the data space, intervals or particular statistical distributions. Clustering can therefore be formulated as a multi-objective optimization problem. The appropriate clustering algorithm and parameter settings (including parameters such as the distance function to use, a density threshold or the number of expected clusters) depend on the individual data set and intended use of the results. Cluster analysis as such is not an automatic task, but an iterative process of knowledge discovery or interactive multi-objective optimization that involves trial and failure. It is often necessary to modify data preprocessing and model parameters until the result achieves the desired properties.
-# Table of Contents
+## Table of Contents
1. [Data Preparation](#data-preparation)
2. [Model Selection](#model-selection)
diff --git a/docs/source/Home/Introduction.md b/docs/source/Home/Introduction.md
index 521b7b61..7063c32e 100644
--- a/docs/source/Home/Introduction.md
+++ b/docs/source/Home/Introduction.md
@@ -307,13 +307,12 @@ The whole package is under construction and the documentation is progressively e
+ Mengying Ye (Mary, Jilin University, China)
+ Mengqi Gao (China University of Geosciences, Beijing, China)
+ Chengtu Li（Trenki, Henan Polytechnic University, Beijing, China）
++ Yucheng Yan (Andy, University of Sydney, Australia)
**Product Group**:
+ Yang Lyu (Daisy, Zhejiang University, China)
-+ Keran Li (Kirk, Chengdu University of Technology, China)
+ Bailun Jiang (EPSI / Lille University, France)
-+ Yucheng Yan (Andy, University of Sydney, Australia)
+ Ruitao Chang (China University of Geosciences Beijing, China)
+ Junchi Liao(Roceda, University of Electronic Science and Technology of China, China)
+ Panyan Weng (The University of Sydney, Australia)
@@ -389,6 +388,7 @@ More Videos will be recorded soon.
+ Qiuhao Zhao (Brad, Zhejiang University, China)
+ Kaixin Zheng (Hayne, Sun Yat-sen University, China)
+ Anzhou Li (Andrian, Zhejiang University, China)
++ Keran Li (Kirk, Chengdu University of Technology, China)
+ Dan Hu (Notre Dame University, United States)
+ Xunxin Liu (Tante, China University of Geosciences, Wuhan, China)
+ Fang Li (liv, Shenzhen University, China)
diff --git a/geochemistrypi/data_mining/data/data_readiness.py b/geochemistrypi/data_mining/data/data_readiness.py
index bb478ca8..6ea0e170 100644
--- a/geochemistrypi/data_mining/data/data_readiness.py
+++ b/geochemistrypi/data_mining/data/data_readiness.py
@@ -140,7 +140,7 @@ def create_sub_data_set(data: pd.DataFrame, allow_empty_columns: bool = False) -
The data set to be processed.
allow_empty_columns : bool, optional
- Whether to include empty columns in the sub data set. The default is Ture.
+ Whether to include empty columns in the sub data set. The default is False.
Returns
-------
@@ -247,8 +247,7 @@ def create_sub_data_set(data: pd.DataFrame, allow_empty_columns: bool = False) -
v_value = int(df_test.isnull().sum())
if not allow_empty_columns and v_value == len(df_test):
print(f"Warning: The selected column {df_test.columns.values} is an empty column! It will be automatically removed.")
- judge = False
- elif df_test[test_columns[0]].dtype in ["int64", "float64"]:
+ if df_test[test_columns[0]].dtype in ["int64", "float64"]:
continue
else:
print(f"Warning: The data type of selected column {df_test.columns.values} is not numeric!" " Please make sure that the selected data type is numeric and re-enter.")