Added first version

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["solara", "run", "app.py", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,165 @@
+#%%
+import solara
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import MinMaxScaler, StandardScaler
+from matplotlib.figure import Figure
+from sklearn.decomposition import PCA
+import plotly.express as px
+from sklearn.manifold import TSNE, Isomap, LocallyLinearEmbedding, SpectralEmbedding
+
+
+# Global non-reactive variablea
+df_original = pd.read_csv('nea_051022.csv')
+all_features = list(df_original.columns)
+default_features = ['a','e','i','om','w','q','ad','H']
+scalers = ['none','minmax','standard']
+feature_extractors = ['none','pca']
+training_ratio_default = 5
+
+# Global reactive variables
+drop_nans = solara.reactive(True)
+features = solara.reactive(default_features)
+feature_maps = {f: solara.reactive('x') for f in all_features}
+scaler = solara.reactive('none')
+training_ratio = solara.reactive(training_ratio_default)
+feature_extractor = solara.reactive('none')
+info_message = solara.reactive("")
+df = solara.reactive(df_original[features.value].copy)
+
+@solara.component
+def process_data():
+    df_out = df_original[features.value].copy()
+    df_out = df_out.dropna() if drop_nans.value else df_out
+    df_out = df_out.sample(frac=training_ratio.value/100.0, random_state=42)
+    print('processing trn ratio',training_ratio.value)
+    info_string = ""
+    for f in features.value:
+        x = df_out[f].to_numpy()
+        y = eval(feature_maps[f].value)
+        df_out.loc[:,f] = y
+
+    if scaler.value != 'none':
+        if scaler.value == 'minmax':
+            transformer = MinMaxScaler()
+        elif scaler.value == 'standard':
+            transformer = StandardScaler()
+        else:
+            transformer = StandardScaler()  
+        try:
+            transformer = transformer.fit(df_out)
+            df_out = pd.DataFrame(transformer.transform(df_out), columns=df_out.columns, index=df_out.index)
+        except Exception as e:
+            df_out = None
+            info_string = str(e)
+    df.set(df_out)
+    solara.DataFrame(df_out, items_per_page=5) 
+    #info_message.set(info_string)
+
+
+
+def reset():
+    features.value = default_features
+    drop_nans.set(True)
+    training_ratio.set(training_ratio_default)
+    for f in all_features:
+        feature_maps[f].set('x')
+        feature_extractor.set('none')
+        scaler.set('none')
+
+
+@solara.component
+def InfoBox():
+    if len(info_message.value) > 0:
+        solara.Error(info_message.value)
+
+@solara.component 
+def BoxPlot():
+    if df.value is None:
+        return
+    fig = Figure()
+    ax = fig.subplots()
+    df.value.plot.box(figsize=(20,5), ax=ax)
+
+    ymin = min(df.value.min(numeric_only=True))
+    ymax = max(df.value.max(numeric_only=True))
+
+    yrange = solara.use_reactive((ymin, ymax))
+    ax.set_ylim(yrange.value[0], yrange.value[1])
+
+    solara.SliderRangeFloat("yrange min and max", value=yrange,min=ymin, max=ymax)
+    solara.FigureMatplotlib(fig)
+    solara.Markdown(f'{yrange}')
+
+
+@solara.component
+def EmbeddingPlot():
+    embedding_method, set_embedding_method = solara.use_state('PCA')
+    n_components, set_n_component = solara.use_state(2)
+    
+    with solara.Row():
+        solara.ToggleButtonsSingle(value=embedding_method, values=['PCA','TSNE','ISOMAP','LLE','SE'], on_value=set_embedding_method)
+        solara.Select(label="Embedding Dimension", value=n_components, values=[1,2,3], on_value=set_n_component)
+        #solara.SliderInt(label='n_components', value=n_components, min=1, max=3, on_value=set_n_component)
+
+    if embedding_method == 'PCA':
+        embedder = PCA(n_components=n_components)
+    elif embedding_method == 'TSNE':
+        embedder = TSNE(n_components=n_components)    
+    elif embedding_method == 'ISOMAP':
+        embedder = Isomap(n_components=n_components)
+    elif embedding_method == 'LLE':
+        embedder = LocallyLinearEmbedding(n_components=n_components)
+    elif embedding_method == 'SE':
+        embedder = SpectralEmbedding(n_components=n_components)
+    else:
+        embedder = PCA(n_components=n_components)
+
+    data_embedded = embedder.fit_transform(df.value)
+    df_embedded = pd.DataFrame(data_embedded)
+    df_embedded['pha'] = list(df_original.loc[df.value.index,'pha'])
+    df_embedded['moid'] = list(df_original.loc[df.value.index,'moid'])
+    print(df_embedded.head())
+    if n_components == 1:
+        fig = px.scatter(df_embedded, x=0, y='moid', color='pha', width=1024, height=768)
+    elif n_components == 2:
+        fig = px.scatter(df_embedded, x=0,y=1,color='moid',symbol='pha', width=1024, height=768)
+    elif n_components == 3:
+        fig = px.scatter_3d(df_embedded, x=0,y=1,z=2,color='moid',symbol='pha', width=1024, height=768)
+    
+    solara.FigurePlotly(fig)
+
+@solara.component
+def Page():
+    with solara.Card(title="Original Raw Data"):
+        solara.DataFrame(df_original, items_per_page=5)
+    with solara.Card(title="Transformed Data"):
+        process_data() # features, feature_maps, drop_nans, scaler, training_ratio) 
+   
+    solara.Button(label='Reset', on_click=reset)
+    solara.ToggleButtonsMultiple(features, all_features)
+
+    with solara.GridFixed(columns=10):
+        for f in features.value:
+            solara.InputText(label=f, value=feature_maps[f], on_value=lambda text : feature_maps[f].set(text))
+    
+    with solara.Row():
+        solara.Checkbox(label='Drop Nans', value=drop_nans, on_value=lambda value : drop_nans.set(value))
+        solara.ToggleButtonsSingle(value=scaler, values=scalers)
+        solara.SliderInt(label='Training Ratio %', value=training_ratio, min=1, max=99)
+    
+    #solara.Markdown(f"""
+    #                # Drop_nans: {drop_nans.value} 
+    #                # trn_ratio {training_ratio.value} 
+    #                # features: {features.value}
+    #                # scaler: {scaler.value} 
+    #                # feature_maps: {feature_maps}
+    #                # info_message: {info_message.value}
+    #                """)
+    InfoBox()
+    EmbeddingPlot()
+    BoxPlot() 
+    
+
+Page()
+

requirements.txt

@@ -0,0 +1,2 @@
+solara
+pandas