angels 0.1.0__tar.gz

angels-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 aa-ds-kits
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

angels-0.1.0/PKG-INFO

@@ -0,0 +1,19 @@
+Metadata-Version: 2.4
+Name: angels
+Version: 0.1.0
+Summary: 数据分析过程工具整合包
+Author: Author
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+License-File: LICENSE
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: scikit-learn
+Requires-Dist: requests
+Requires-Dist: beautifulsoup4
+Requires-Dist: pymysql
+Dynamic: license-file

angels-0.1.0/README.md

@@ -0,0 +1,96 @@
+# angels
+
+数据分析过程工具整合包，包含数据获取、数据清洗、逻辑加工、分析算法、可视化等五个核心模块。
+
+## 安装
+
+```bash
+pip install angels
+```
+
+## 打包说明
+
+本项目使用现代的 `pyproject.toml` 打包方式，替代了传统的 `setup.py`。
+
+## 核心模块
+
+### 1. 数据获取 (data_acquisition)
+
+- `load_csv(file_path)`: 加载CSV文件
+- `load_excel(file_path, sheet_name=0)`: 加载Excel文件
+- `load_json(file_path)`: 加载JSON文件
+- `load_from_api(url, params=None)`: 从API获取数据
+- `load_from_web(url, table_selector)`: 从网页表格获取数据
+
+### 2. 数据清洗 (data_cleaning)
+
+- `remove_duplicates(df)`: 移除重复行
+- `handle_missing_values(df, strategy='drop', fill_value=None)`: 处理缺失值
+- `convert_data_types(df, dtypes=None)`: 转换数据类型
+- `remove_outliers(df, columns=None, method='iqr', threshold=1.5)`: 移除异常值
+- `standardize_columns(df)`: 标准化列名
+
+### 3. 逻辑加工 (logic_processing)
+
+- `group_by_aggregate(df, group_by, aggregations)`: 按列分组并聚合
+- `pivot_table(df, index, columns, values, aggfunc='mean')`: 创建透视表
+- `calculate_rolling_stats(df, column, window, stats=['mean', 'std'])`: 计算滚动统计量
+- `calculate_diff(df, column, periods=1)`: 计算差值
+- `merge_dataframes(df1, df2, on=None, how='inner')`: 合并数据框
+- `create_features(df)`: 创建特征
+
+### 4. 分析算法 (analysis_algorithms)
+
+- `descriptive_statistics(df)`: 计算描述性统计量
+- `correlation_analysis(df, method='pearson')`: 计算相关性矩阵
+- `kmeans_clustering(df, n_clusters=3, random_state=42)`: K均值聚类
+- `linear_regression(X, y)`: 线性回归
+- `time_series_analysis(df, time_column, value_column)`: 时间序列分析
+- `hypothesis_testing(sample1, sample2)`: 假设检验
+
+### 5. 可视化 (visualization)
+
+- `plot_histogram(df, column, bins=30, title=None)`: 绘制直方图
+- `plot_scatter(df, x, y, hue=None, title=None)`: 绘制散点图
+- `plot_bar(df, x, y, title=None)`: 绘制柱状图
+- `plot_box(df, x, y=None, title=None)`: 绘制箱线图
+- `plot_correlation_heatmap(df, title=None)`: 绘制相关性热图
+- `plot_time_series(df, x, y, title=None)`: 绘制时间序列图
+
+## 使用示例
+
+```python
+from angels import *
+
+# 1. 数据获取
+df = load_csv('data.csv')
+
+# 2. 数据清洗
+df = remove_duplicates(df)
+df = handle_missing_values(df, strategy='mean')
+df = standardize_columns(df)
+
+# 3. 逻辑加工
+df = group_by_aggregate(df, 'category', {'value': 'sum'})
+
+# 4. 分析算法
+stats = descriptive_statistics(df)
+corr = correlation_analysis(df)
+
+# 5. 可视化
+plt = plot_histogram(df, 'value')
+plt.show()
+
+plt = plot_correlation_heatmap(df)
+plt.show()
+```
+
+## 依赖
+
+- pandas
+- numpy
+- matplotlib
+- seaborn
+- scikit-learn
+- requests
+- beautifulsoup4

angels-0.1.0/pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "angels"
+version = "0.1.0"
+description = "数据分析过程工具整合包"
+authors = [
+    { name = "Author" }
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+requires-python = ">=3.6"
+dependencies = [
+    "pandas",
+    "numpy",
+    "matplotlib",
+    "seaborn",
+    "scikit-learn",
+    "requests",
+    "beautifulsoup4",
+    "pymysql"
+]
+
+

angels-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

angels-0.1.0/src/angels/__init__.py

@@ -0,0 +1,7 @@
+__version__ = "0.1.0"
+
+from .data_acquisition import *
+from .data_cleaning import *
+from .logic_processing import *
+from .analysis_algorithms import *
+from .visualization import *

angels-0.1.0/src/angels/analysis_algorithms/__init__.py

@@ -0,0 +1 @@
+from .analysis_algorithms import *

angels-0.1.0/src/angels/analysis_algorithms/analysis_algorithms.py

@@ -0,0 +1,48 @@
+import pandas as pd
+import numpy as np
+from sklearn.cluster import KMeans
+from sklearn.linear_model import LinearRegression
+from sklearn.preprocessing import StandardScaler
+
+def descriptive_statistics(df):
+    """计算描述性统计量"""
+    return df.describe()
+
+def correlation_analysis(df, method='pearson'):
+    """计算相关性矩阵"""
+    return df.corr(method=method)
+
+def kmeans_clustering(df, n_clusters=3, random_state=42):
+    """K均值聚类"""
+    scaler = StandardScaler()
+    scaled_data = scaler.fit_transform(df.select_dtypes(include=[np.number]))
+    kmeans = KMeans(n_clusters=n_clusters, random_state=random_state)
+    clusters = kmeans.fit_predict(scaled_data)
+    df['cluster'] = clusters
+    return df, kmeans
+
+def linear_regression(X, y):
+    """线性回归"""
+    model = LinearRegression()
+    model.fit(X, y)
+    predictions = model.predict(X)
+    return model, predictions
+
+def time_series_analysis(df, time_column, value_column):
+    """时间序列分析"""
+    df[time_column] = pd.to_datetime(df[time_column])
+    df = df.sort_values(time_column)
+    df.set_index(time_column, inplace=True)
+    
+    # 计算移动平均
+    df['moving_average'] = df[value_column].rolling(window=7).mean()
+    # 计算同比增长
+    df['year_over_year'] = df[value_column].pct_change(periods=365)
+    
+    return df
+
+def hypothesis_testing(sample1, sample2):
+    """假设检验"""
+    from scipy import stats
+    t_stat, p_value = stats.ttest_ind(sample1, sample2)
+    return t_stat, p_value

angels-0.1.0/src/angels/data_acquisition/__init__.py

@@ -0,0 +1 @@
+from .data_acquisition import *

angels-0.1.0/src/angels/data_acquisition/data_acquisition.py

@@ -0,0 +1,85 @@
+import pandas as pd
+import requests
+from bs4 import BeautifulSoup
+import json
+import pymysql
+from pymysql.cursors import DictCursor
+import os
+
+def load_csv(file_path):
+    """加载CSV文件"""
+    return pd.read_csv(file_path)
+
+def load_excel(file_path, sheet_name=0):
+    """加载Excel文件"""
+    return pd.read_excel(file_path, sheet_name=sheet_name)
+
+def load_json(file_path):
+    """加载JSON文件"""
+    with open(file_path, 'r', encoding='utf-8') as f:
+        data = json.load(f)
+    return pd.DataFrame(data)
+
+def load_from_api(url, params=None):
+    """从API获取数据"""
+    response = requests.get(url, params=params)
+    response.raise_for_status()
+    return pd.DataFrame(response.json())
+
+def load_from_web(url, table_selector):
+    """从网页表格获取数据"""
+    response = requests.get(url)
+    response.raise_for_status()
+    soup = BeautifulSoup(response.content, 'html.parser')
+    table = soup.select_one(table_selector)
+    return pd.read_html(str(table))[0]
+
+def get_db_config():
+    """获取数据库配置"""
+    # 从环境变量获取配置文件路径，不设置默认值
+    CONFIG_PATH = os.getenv('DB_INFO')
+    if not CONFIG_PATH:
+        # 环境变量未设置时的提示
+        error_msg = "环境变量 DB_INFO 未设置。请按照以下方式配置：\n"
+        error_msg += "1. 环境变量配置：\n"
+        error_msg += "   - Windows (图形界面): 设置环境变量 DB_INFO 为配置文件路径\n"
+        error_msg += "   - Windows (PowerShell): 执行 $env:DB_INFO='配置文件路径'\n"
+        error_msg += "   - Linux/Mac: 执行 export DB_INFO=配置文件路径\n"
+        raise ValueError(error_msg)
+    
+    try:
+        # 尝试读取配置文件
+        with open(CONFIG_PATH) as f:
+            return json.load(f)
+    except FileNotFoundError:
+        # 文件不存在时的提示
+        error_msg = f"配置文件 {CONFIG_PATH} 不存在。请确保文件路径正确。\n"
+        raise FileNotFoundError(error_msg)
+    except PermissionError:
+        # 权限不足时的提示
+        raise PermissionError(f"没有权限读取配置文件 {CONFIG_PATH}")
+
+DB_CONFIG = get_db_config()
+
+def fetch_dataframe(sql, db_name='rpt'):
+    """从数据库获取DataFrame"""
+    if db_name not in DB_CONFIG:
+        raise ValueError(f"未知数据库标识: {db_name}")
+    # 使用配置文件中的连接信息
+    conn_params = DB_CONFIG[db_name]
+    conn = pymysql.connect(**conn_params)
+    
+    try:
+        with conn.cursor(DictCursor) as cursor:
+            cursor.execute(sql)
+            res = cursor.fetchall()
+            if res:
+                df = pd.DataFrame(res)
+            else:
+                # 如果没有数据，返回空DataFrame
+                df = pd.DataFrame()
+            return df
+    except Exception as e:
+        raise e
+    finally:
+        conn.close()

angels-0.1.0/src/angels/data_cleaning/__init__.py

@@ -0,0 +1 @@
+from .data_cleaning import *

angels-0.1.0/src/angels/data_cleaning/data_cleaning.py

@@ -0,0 +1,50 @@
+import pandas as pd
+import numpy as np
+
+def remove_duplicates(df):
+    """移除重复行"""
+    return df.drop_duplicates()
+
+def handle_missing_values(df, strategy='drop', fill_value=None):
+    """处理缺失值"""
+    if strategy == 'drop':
+        return df.dropna()
+    elif strategy == 'fill':
+        return df.fillna(fill_value)
+    elif strategy == 'mean':
+        return df.fillna(df.mean())
+    elif strategy == 'median':
+        return df.fillna(df.median())
+    else:
+        raise ValueError("Invalid strategy. Use 'drop', 'fill', 'mean', or 'median'")
+
+def convert_data_types(df, dtypes=None):
+    """转换数据类型"""
+    if dtypes:
+        return df.astype(dtypes)
+    else:
+        return df.infer_objects()
+
+def remove_outliers(df, columns=None, method='iqr', threshold=1.5):
+    """移除异常值"""
+    if columns is None:
+        columns = df.select_dtypes(include=[np.number]).columns
+    
+    for col in columns:
+        if method == 'iqr':
+            Q1 = df[col].quantile(0.25)
+            Q3 = df[col].quantile(0.75)
+            IQR = Q3 - Q1
+            lower_bound = Q1 - threshold * IQR
+            upper_bound = Q3 + threshold * IQR
+            df = df[(df[col] >= lower_bound) & (df[col] <= upper_bound)]
+        elif method == 'zscore':
+            z_scores = np.abs((df[col] - df[col].mean()) / df[col].std())
+            df = df[z_scores < threshold]
+    
+    return df
+
+def standardize_columns(df):
+    """标准化列名"""
+    df.columns = [col.strip().lower().replace(' ', '_') for col in df.columns]
+    return df

angels-0.1.0/src/angels/logic_processing/__init__.py

@@ -0,0 +1 @@
+from .logic_processing import *

angels-0.1.0/src/angels/logic_processing/logic_processing.py

@@ -0,0 +1,38 @@
+import pandas as pd
+import numpy as np
+
+def group_by_aggregate(df, group_by, aggregations):
+    """按列分组并聚合"""
+    return df.groupby(group_by).agg(aggregations).reset_index()
+
+def pivot_table(df, index, columns, values, aggfunc='mean'):
+    """创建透视表"""
+    return pd.pivot_table(df, index=index, columns=columns, values=values, aggfunc=aggfunc)
+
+def calculate_rolling_stats(df, column, window, stats=['mean', 'std']):
+    """计算滚动统计量"""
+    for stat in stats:
+        if stat == 'mean':
+            df[f'{column}_rolling_{window}_mean'] = df[column].rolling(window=window).mean()
+        elif stat == 'std':
+            df[f'{column}_rolling_{window}_std'] = df[column].rolling(window=window).std()
+        elif stat == 'sum':
+            df[f'{column}_rolling_{window}_sum'] = df[column].rolling(window=window).sum()
+    return df
+
+def calculate_diff(df, column, periods=1):
+    """计算差值"""
+    df[f'{column}_diff_{periods}'] = df[column].diff(periods=periods)
+    return df
+
+def merge_dataframes(df1, df2, on=None, how='inner'):
+    """合并数据框"""
+    return pd.merge(df1, df2, on=on, how=how)
+
+def create_features(df):
+    """创建特征"""
+    # 示例特征创建
+    for col in df.select_dtypes(include=[np.number]).columns:
+        df[f'{col}_log'] = np.log(df[col] + 1)  # 对数变换
+        df[f'{col}_squared'] = df[col] ** 2  # 平方
+    return df

angels-0.1.0/src/angels/visualization/__init__.py

@@ -0,0 +1 @@
+from .visualization import *

angels-0.1.0/src/angels/visualization/visualization.py

@@ -0,0 +1,62 @@
+import matplotlib.pyplot as plt
+import seaborn as sns
+import pandas as pd
+import numpy as np
+
+def plot_histogram(df, column, bins=30, title=None):
+    """绘制直方图"""
+    plt.figure(figsize=(10, 6))
+    sns.histplot(df[column], bins=bins, kde=True)
+    plt.title(title or f'{column} 分布')
+    plt.xlabel(column)
+    plt.ylabel('频率')
+    plt.tight_layout()
+    return plt
+
+def plot_scatter(df, x, y, hue=None, title=None):
+    """绘制散点图"""
+    plt.figure(figsize=(10, 6))
+    sns.scatterplot(data=df, x=x, y=y, hue=hue)
+    plt.title(title or f'{x} vs {y}')
+    plt.tight_layout()
+    return plt
+
+def plot_bar(df, x, y, title=None):
+    """绘制柱状图"""
+    plt.figure(figsize=(10, 6))
+    sns.barplot(data=df, x=x, y=y)
+    plt.title(title or f'{y} by {x}')
+    plt.xticks(rotation=45)
+    plt.tight_layout()
+    return plt
+
+def plot_box(df, x, y=None, title=None):
+    """绘制箱线图"""
+    plt.figure(figsize=(10, 6))
+    if y:
+        sns.boxplot(data=df, x=x, y=y)
+    else:
+        sns.boxplot(data=df[x])
+    plt.title(title or f'{y or x} 分布')
+    plt.xticks(rotation=45)
+    plt.tight_layout()
+    return plt
+
+def plot_correlation_heatmap(df, title=None):
+    """绘制相关性热图"""
+    plt.figure(figsize=(12, 10))
+    corr = df.corr()
+    sns.heatmap(corr, annot=True, cmap='coolwarm', vmin=-1, vmax=1)
+    plt.title(title or '相关性矩阵')
+    plt.tight_layout()
+    return plt
+
+def plot_time_series(df, x, y, title=None):
+    """绘制时间序列图"""
+    plt.figure(figsize=(12, 6))
+    plt.plot(df[x], df[y])
+    plt.title(title or f'{y} 时间序列')
+    plt.xlabel('时间')
+    plt.ylabel(y)
+    plt.tight_layout()
+    return plt

angels-0.1.0/src/angels.egg-info/PKG-INFO

@@ -0,0 +1,19 @@
+Metadata-Version: 2.4
+Name: angels
+Version: 0.1.0
+Summary: 数据分析过程工具整合包
+Author: Author
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+License-File: LICENSE
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: scikit-learn
+Requires-Dist: requests
+Requires-Dist: beautifulsoup4
+Requires-Dist: pymysql
+Dynamic: license-file

angels-0.1.0/src/angels.egg-info/SOURCES.txt

@@ -0,0 +1,19 @@
+LICENSE
+README.md
+pyproject.toml
+src/angels/__init__.py
+src/angels.egg-info/PKG-INFO
+src/angels.egg-info/SOURCES.txt
+src/angels.egg-info/dependency_links.txt
+src/angels.egg-info/requires.txt
+src/angels.egg-info/top_level.txt
+src/angels/analysis_algorithms/__init__.py
+src/angels/analysis_algorithms/analysis_algorithms.py
+src/angels/data_acquisition/__init__.py
+src/angels/data_acquisition/data_acquisition.py
+src/angels/data_cleaning/__init__.py
+src/angels/data_cleaning/data_cleaning.py
+src/angels/logic_processing/__init__.py
+src/angels/logic_processing/logic_processing.py
+src/angels/visualization/__init__.py
+src/angels/visualization/visualization.py

angels-0.1.0/src/angels.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

angels-0.1.0/src/angels.egg-info/requires.txt

@@ -0,0 +1,8 @@
+pandas
+numpy
+matplotlib
+seaborn
+scikit-learn
+requests
+beautifulsoup4
+pymysql

angels-0.1.0/src/angels.egg-info/top_level.txt

@@ -0,0 +1 @@
+angels