Upload 15 files

app.py

@@ -1,3 +1,37 @@
+### 简介
 import simplestart as ss
 
-ss.write("Hello, world")
+ss.md('''
+## Iris 数据集
+Iris数据集是常用的分类实验数据集，由Fisher, 1936收集整理。Iris也称鸢尾花卉数据集，是一类多重变量分析的数据集。数据集包含150个数据样本，分为3类，每类50个数据，每个数据包含4个属性。可通过花萼长度，花萼宽度，花瓣长度，花瓣宽度4个属性预测鸢尾花卉属于（Setosa，Versicolour，Virginica）三个种类中的哪一类。
+
+### 鸢尾花
+鸢尾的文化底蕴深厚，鸢尾花因花瓣形如鸢鸟尾巴而称之，其拉丁属名“iris” 为希腊语“彩虹”之意，喻指花色丰富。
+''')
+
+
+with ss.row(style="margin:10px 0"):
+    with ss.col():
+        ss.image("./images/setosa.webp", title = "丝质鸢尾 setosa", elevation = 10, width=250)
+
+    with ss.col():
+        ss.image("./images/versicolor.webp", title = "鸢尾花 versicolor", elevation = 10, width=250)
+
+    with ss.col():
+        ss.image("./images/virginica.webp", title = "弗吉尼亚鸢尾 virginica", elevation = 10, width=250)
+    
+ss.md('''
+### 机器学习
+
+这个教程将使用 scikit-learn 库构建一个机器学习分类模型，以预测鸢尾花的品种，具体说就是利用鸢尾花的测量数据——包括花瓣和花萼的长度及宽度训练和测试模型。我们的目标是通过应用几个经典的机器学习算法，教会模型如何从这些已标记的数据中学习，以便能对新的鸢尾花进行准确的品种预测。
+
+''')
+
+ss.md('''
+###
+本例的网络参考资料有:
+---
+[1.【机器学习基础】1.7 鸢尾花分类](https://blog.csdn.net/qq_47809408/article/details/124632290)
+[2. KNN分类算法介绍，用KNN分类鸢尾花数据集（iris）](https://blog.csdn.net/weixin_51756038/article/details/130096706)
+[3. Interactive Web App with Streamlit and Scikit-learn](https://github.com/patrickloeber/streamlit-demo)
+''')

data/iris.csv

@@ -0,0 +1,151 @@
+sepal_length,sepal_width,petal_length,petal_width,species
+5.1,3.5,1.4,0.2,setosa
+4.9,3.0,1.4,0.2,setosa
+4.7,3.2,1.3,0.2,setosa
+4.6,3.1,1.5,0.2,setosa
+5.0,3.6,1.4,0.2,setosa
+5.4,3.9,1.7,0.4,setosa
+4.6,3.4,1.4,0.3,setosa
+5.0,3.4,1.5,0.2,setosa
+4.4,2.9,1.4,0.2,setosa
+4.9,3.1,1.5,0.1,setosa
+5.4,3.7,1.5,0.2,setosa
+4.8,3.4,1.6,0.2,setosa
+4.8,3.0,1.4,0.1,setosa
+4.3,3.0,1.1,0.1,setosa
+5.8,4.0,1.2,0.2,setosa
+5.7,4.4,1.5,0.4,setosa
+5.4,3.9,1.3,0.4,setosa
+5.1,3.5,1.4,0.3,setosa
+5.7,3.8,1.7,0.3,setosa
+5.1,3.8,1.5,0.3,setosa
+5.4,3.4,1.7,0.2,setosa
+5.1,3.7,1.5,0.4,setosa
+4.6,3.6,1.0,0.2,setosa
+5.1,3.3,1.7,0.5,setosa
+4.8,3.4,1.9,0.2,setosa
+5.0,3.0,1.6,0.2,setosa
+5.0,3.4,1.6,0.4,setosa
+5.2,3.5,1.5,0.2,setosa
+5.2,3.4,1.4,0.2,setosa
+4.7,3.2,1.6,0.2,setosa
+4.8,3.1,1.6,0.2,setosa
+5.4,3.4,1.5,0.4,setosa
+5.2,4.1,1.5,0.1,setosa
+5.5,4.2,1.4,0.2,setosa
+4.9,3.1,1.5,0.2,setosa
+5.0,3.2,1.2,0.2,setosa
+5.5,3.5,1.3,0.2,setosa
+4.9,3.6,1.4,0.1,setosa
+4.4,3.0,1.3,0.2,setosa
+5.1,3.4,1.5,0.2,setosa
+5.0,3.5,1.3,0.3,setosa
+4.5,2.3,1.3,0.3,setosa
+4.4,3.2,1.3,0.2,setosa
+5.0,3.5,1.6,0.6,setosa
+5.1,3.8,1.9,0.4,setosa
+4.8,3.0,1.4,0.3,setosa
+5.1,3.8,1.6,0.2,setosa
+4.6,3.2,1.4,0.2,setosa
+5.3,3.7,1.5,0.2,setosa
+5.0,3.3,1.4,0.2,setosa
+7.0,3.2,4.7,1.4,versicolor
+6.4,3.2,4.5,1.5,versicolor
+6.9,3.1,4.9,1.5,versicolor
+5.5,2.3,4.0,1.3,versicolor
+6.5,2.8,4.6,1.5,versicolor
+5.7,2.8,4.5,1.3,versicolor
+6.3,3.3,4.7,1.6,versicolor
+4.9,2.4,3.3,1.0,versicolor
+6.6,2.9,4.6,1.3,versicolor
+5.2,2.7,3.9,1.4,versicolor
+5.0,2.0,3.5,1.0,versicolor
+5.9,3.0,4.2,1.5,versicolor
+6.0,2.2,4.0,1.0,versicolor
+6.1,2.9,4.7,1.4,versicolor
+5.6,2.9,3.6,1.3,versicolor
+6.7,3.1,4.4,1.4,versicolor
+5.6,3.0,4.5,1.5,versicolor
+5.8,2.7,4.1,1.0,versicolor
+6.2,2.2,4.5,1.5,versicolor
+5.6,2.5,3.9,1.1,versicolor
+5.9,3.2,4.8,1.8,versicolor
+6.1,2.8,4.0,1.3,versicolor
+6.3,2.5,4.9,1.5,versicolor
+6.1,2.8,4.7,1.2,versicolor
+6.4,2.9,4.3,1.3,versicolor
+6.6,3.0,4.4,1.4,versicolor
+6.8,2.8,4.8,1.4,versicolor
+6.7,3.0,5.0,1.7,versicolor
+6.0,2.9,4.5,1.5,versicolor
+5.7,2.6,3.5,1.0,versicolor
+5.5,2.4,3.8,1.1,versicolor
+5.5,2.4,3.7,1.0,versicolor
+5.8,2.7,3.9,1.2,versicolor
+6.0,2.7,5.1,1.6,versicolor
+5.4,3.0,4.5,1.5,versicolor
+6.0,3.4,4.5,1.6,versicolor
+6.7,3.1,4.7,1.5,versicolor
+6.3,2.3,4.4,1.3,versicolor
+5.6,3.0,4.1,1.3,versicolor
+5.5,2.5,4.0,1.3,versicolor
+5.5,2.6,4.4,1.2,versicolor
+6.1,3.0,4.6,1.4,versicolor
+5.8,2.6,4.0,1.2,versicolor
+5.0,2.3,3.3,1.0,versicolor
+5.6,2.7,4.2,1.3,versicolor
+5.7,3.0,4.2,1.2,versicolor
+5.7,2.9,4.2,1.3,versicolor
+6.2,2.9,4.3,1.3,versicolor
+5.1,2.5,3.0,1.1,versicolor
+5.7,2.8,4.1,1.3,versicolor
+6.3,3.3,6.0,2.5,virginica
+5.8,2.7,5.1,1.9,virginica
+7.1,3.0,5.9,2.1,virginica
+6.3,2.9,5.6,1.8,virginica
+6.5,3.0,5.8,2.2,virginica
+7.6,3.0,6.6,2.1,virginica
+4.9,2.5,4.5,1.7,virginica
+7.3,2.9,6.3,1.8,virginica
+6.7,2.5,5.8,1.8,virginica
+7.2,3.6,6.1,2.5,virginica
+6.5,3.2,5.1,2.0,virginica
+6.4,2.7,5.3,1.9,virginica
+6.8,3.0,5.5,2.1,virginica
+5.7,2.5,5.0,2.0,virginica
+5.8,2.8,5.1,2.4,virginica
+6.4,3.2,5.3,2.3,virginica
+6.5,3.0,5.5,1.8,virginica
+7.7,3.8,6.7,2.2,virginica
+7.7,2.6,6.9,2.3,virginica
+6.0,2.2,5.0,1.5,virginica
+6.9,3.2,5.7,2.3,virginica
+5.6,2.8,4.9,2.0,virginica
+7.7,2.8,6.7,2.0,virginica
+6.3,2.7,4.9,1.8,virginica
+6.7,3.3,5.7,2.1,virginica
+7.2,3.2,6.0,1.8,virginica
+6.2,2.8,4.8,1.8,virginica
+6.1,3.0,4.9,1.8,virginica
+6.4,2.8,5.6,2.1,virginica
+7.2,3.0,5.8,1.6,virginica
+7.4,2.8,6.1,1.9,virginica
+7.9,3.8,6.4,2.0,virginica
+6.4,2.8,5.6,2.2,virginica
+6.3,2.8,5.1,1.5,virginica
+6.1,2.6,5.6,1.4,virginica
+7.7,3.0,6.1,2.3,virginica
+6.3,3.4,5.6,2.4,virginica
+6.4,3.1,5.5,1.8,virginica
+6.0,3.0,4.8,1.8,virginica
+6.9,3.1,5.4,2.1,virginica
+6.7,3.1,5.6,2.4,virginica
+6.9,3.1,5.1,2.3,virginica
+5.8,2.7,5.1,1.9,virginica
+6.8,3.2,5.9,2.3,virginica
+6.7,3.3,5.7,2.5,virginica
+6.7,3.0,5.2,2.3,virginica
+6.3,2.5,5.0,1.9,virginica
+6.5,3.0,5.2,2.0,virginica
+6.2,3.4,5.4,2.3,virginica
+5.9,3.0,5.1,1.8,virginica

data/model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37d94112cf51c382e9639ba7d9aab490170f2aa684455aa589c0c097dbdb929
+size 912

pages/01data_intro.py

@@ -0,0 +1,35 @@
+### 数据浏览
+import simplestart as ss
+import pandas as pd
+
+ss.md('''
+## Iris数据集
+数据集包含150个数据样本，分为3类，即Setosa，Versicolour，Virginica。每类50个数据，每个数据包含4个属性。
+''')
+
+ss.space()
+
+title = "表1. Iris数据集"
+subtitle = "sepal_length 花萼长度, sepal_width 花萼宽度, petal_lenght 花瓣长度, petal_width 花瓣宽度"
+# 设置全局浮点数显示精度
+pd.options.display.float_format = '{:.2f}'.format
+df = pd.read_csv("./data/iris.csv")
+
+ss.table(df, index=True, title = title, subtitle = subtitle, width=400)
+
+
+ss.table(df.describe(), index=True)
+
+
+ss.md("---")
+# 模拟数据
+import numpy as np
+# 设置随机种子以确保结果可重复
+np.random.seed(0)
+
+num_rows = 10000
+data = {
+    'Column1': np.random.randint(0, 100, size=num_rows),  # 随机整数
+    'Column2': np.random.random(size=num_rows),            # 随机浮点数
+    'Column3': np.random.choice(['A', 'B', 'C', 'D'], size=num_rows),  # 随机选择的类别
+}

pages/02data_feature.py

@@ -0,0 +1,57 @@
+### 特征分析
+
+import simplestart as ss
+import pandas as pd
+
+ss.md('''
+## 特征分析
+''')
+
+ss.space()
+
+ss.md("#### 1. 特征的散点矩阵")
+ss.space()
+ss.image("./images/feature01.png", width=600, height = 500)
+
+ss.space()
+
+ss.md('''
+本图来自:
+[VuNus 【机器学习基础】1.7 鸢尾花分类](https://blog.csdn.net/qq_47809408/article/details/124632290)
+''')
+
+ss.space()
+ss.md("#### 2. 特征浏览")
+import pandas as pd
+from bokeh.plotting import figure, show
+from bokeh.models import ColumnDataSource
+from bokeh.transform import factor_cmap
+from bokeh.embed import file_html
+from bokeh.resources import CDN
+from bokeh.palettes import Category10
+
+# 加载数据集
+data = pd.read_csv("./data/iris.csv")
+
+# 创建 Bokeh 图表
+p = figure(title="Iris 数据集散点图", x_axis_label='花萼长度 (cm)', y_axis_label='花萼宽度 (cm)',
+           tools="pan,wheel_zoom,box_zoom,reset,hover,save", width=800, height=600)
+
+# 创建数据源
+source = ColumnDataSource(data)
+
+# 为 species 列设置颜色映射
+species_list = data['species'].unique().tolist()
+p.circle(x='sepal_length', y='sepal_width', source=source, size=10,
+         color=factor_cmap('species', palette=Category10[3], factors=species_list), legend_field='species')
+
+# 配置图例
+p.legend.title = "Species"
+p.legend.location = "top_left"
+
+# 将 Bokeh 图表转换为 HTML 并显示
+html_output = file_html(p, CDN, "Iris 数据集散点图")
+#show(p)
+
+
+ss.htmlview(html_output)

pages/03model_train.py

@@ -0,0 +1,125 @@
+### 模型训练
+
+import simplestart as ss
+
+from sklearn import datasets
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+
+
+ss.md('''
+## 模型训练
+''')
+
+
+#加载数据，并划分样本数据
+data = datasets.load_iris()
+X = data.data
+y = data.target
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
+
+#页面会话变量
+ss.session["acc"] = ""
+ss.session["code"] = 0
+
+#训练函数 
+def train(event):
+    clf = KNeighborsClassifier(n_neighbors=3)
+    clf.fit(X_train,y_train)
+    
+    y_pred = clf.predict(X_test)
+
+    acc = accuracy_score(y_test, y_pred)
+    acc = round(acc, 2)
+    
+    ss.session["acc"] = acc #将结果赋值给页面会话变量，相应页面显示值会自动响应
+
+ss.md('''
+#### 模型训练的主要步骤:
+首先，从数据集中加载 Iris 数据（包括特征和标签），并将这些数据划分为训练集和测试集，其中 80% 用于训练，20% 用于测试。接着，定义了一个训练函数，该函数使用 K-Nearest Neighbors（KNN）分类器进行训练，评估模型的预测精度，并将结果保存在一个页面会话变量中，以便在网页上显示。
+###
+在网页上，显示了一个训练按钮。当用户点击这个按钮时，训练函数会被触发，模型会在后台进行训练并计算测试集的预测精度。训练完成后，精度结果会更新到页面中，并以“Accuracy = @acc”格式展示给用户，其中 @acc 是训练过程中计算得到的预测精度值。
+###
+训练和测试速度特别快可能是因为 Iris 数据集非常小，只有 150 个样本和 4 个特征。此外，K-Nearest Neighbors（KNN）是一种简单且高效的算法，特别是在小数据集上表现较好，因此训练和测试过程迅速完成。
+###
+---
+''')
+ss.write(f'测试集的预测精度 Accuracy =', "@acc")
+
+ss.button("Train", onclick = train)
+#ui
+
+
+ss.md("---")
+
+def conditioner(event):
+    return ss.session["code"] == 1
+
+def checkcode(event):
+    ss.session["code"] = 1
+    
+def hidecode(event):
+    ss.session["code"] = 0
+
+ss.button("查看代码", onclick = checkcode)
+ss.button("隐藏代码", onclick = hidecode)
+
+with ss.when(conditioner):
+    ss.md('''
+```python
+import simplestart as ss
+
+from sklearn import datasets
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+
+#加载数据，并划分样本数据
+data = datasets.load_iris()
+X = data.data
+y = data.target
+ss.write(X.shape, y.shape)
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
+
+#页面会话变量
+ss.session["acc"] = ""
+
+#训练函数 
+def train(event):
+    clf = KNeighborsClassifier(n_neighbors=3)
+    clf.fit(X_train,y_train)
+
+    y_pred = clf.predict(X_test)
+
+    acc = accuracy_score(y_test, y_pred)
+    acc = round(acc, 2)
+
+    ss.session["acc"] = acc #将结果赋值给页面会话变量，相应页面显示值会自动响应
+
+#显示在测试集上模型的准确率
+ss.write(f'测试集的预测精度 Accuracy =', "\@acc")
+
+ss.button("Train", onclick = train)
+```
+    ''')
+
+
+ss.md("---")
+
+
+ss.md('''
+::: tip
+  ### KNN的优点:
+  简洁、易于理解、易于实现、无须估计参数，无须训练；
+  适合对稀有事件进行分类；
+  特别适用于多分类问题（Multi-label，对象具有多个类别标签）
+:::
+''')
+
+ss.md('''
+更多KNN介绍，请参考
+[KNN分类算法介绍，用KNN分类鸢尾花数据集（iris）](https://blog.csdn.net/weixin_51756038/article/details/130096706)
+''')

pages/04model_sample.py

@@ -0,0 +1,64 @@
+### 预测实例
+#the original source code:
+#https://github.com/AzeemWaqarRao/Streamlit-Iris-Classification-App
+import simplestart as ss
+
+from sklearn.datasets import load_iris
+import pandas as pd
+import pickle
+import numpy as np
+
+#data and api
+species = ['setosa', 'versicolor', 'virginica']
+image = ['./images/setosa.jpg', './images/versicolor.jpg', './images/virginica.jpg']
+with open('./data/model.pkl', 'rb') as f:
+    model = pickle.load(f)
+    
+    
+def slidechange(event):
+    predict()
+
+def predict():
+    # Getting Prediction from model
+    inp = np.array([sepal_length.value, sepal_width.value, petal_length.value, petal_width.value])
+    inp = np.expand_dims(inp,axis=0)
+    prediction = model.predict_proba(inp)
+    #test
+    #prediction = [["aaa", "bbb","cccds sdfdsafd sagdsfasf sdfsdf"]]
+
+    ## Show Results when prediction is done
+    if True:
+        df = pd.DataFrame(prediction, index = ['result'], columns=species).round(4)
+        table_result.data = df
+        ss.session["result"] = species[np.argmax(prediction)]
+        image_flower.image = image[np.argmax(prediction)]
+        
+#ui 
+with ss.sidebar():
+    ss.write("### Inputs")
+    
+    sepal_length = ss.slider("sepal length (cm)",4.3, 7.9, 5.0, onchange=slidechange)
+    
+    sepal_width = ss.slider("sepal width (cm)",2.0,4.4,3.6, onchange=slidechange)
+    petal_length = ss.slider("petal length (cm)",1.0,6.9,1.4, onchange=slidechange)
+    petal_width = ss.slider("petal width (cm)",0.1,2.5,0.2, onchange=slidechange)
+
+
+ss.write("## 鸢尾花分类预测")
+ss.write("改变花萼花瓣的长度宽度，在3种可能的类别中预测")
+
+ss.write('''
+# Results
+Following is the probability of each class
+''')
+
+ss.space()
+
+table_result = ss.table(show_border = True)
+ss.write("**This flower belongs to @result" + " class**")
+
+ss.space()
+
+image_flower = ss.image(image[0])
+    
+predict()