Upload 17 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/celltumor.PNG filter=lfs diff=lfs merge=lfs -text

Dockerfile.txt

@@ -0,0 +1,18 @@
+# Use Python image
+FROM python:3.9
+
+# Set the working directory inside the container
+WORKDIR /code
+
+# Copy the requirements file from the root
+COPY ./requirements.txt /code/requirements.txt
+
+# Install dependencies
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Copy all files and folders (including 'pages' and 'assets')
+COPY . /code
+
+# Start the app using Gunicorn on port 7860
+# This assumes your main file is 'app.py' and it contains 'server = app.server'
+CMD ["gunicorn", "-b", "0.0.0.0:7860", "app:server"]

Procfile

@@ -0,0 +1 @@
+web: gunicorn app:server

app.py

@@ -0,0 +1,48 @@
+import dash
+from dash import html, page_container
+import dash_bootstrap_components as dbc
+
+# ----------------------------#
+# Initialize app
+# ----------------------------#
+app = dash.Dash(
+    __name__,
+    use_pages=True,
+    external_stylesheets=[dbc.themes.BOOTSTRAP],
+    suppress_callback_exceptions=True,
+    title="Breast Cancer Dashboard"
+)
+
+# ----------------------------#
+# Header
+# ----------------------------#
+header = html.Header([
+    html.Div("Breast Cancer Project Dashboard", className="header"),
+    html.Nav([
+        dash.dcc.Link("Introduction", href="/", className="nav-link"),
+        dash.dcc.Link("Data Analysis", href="/data-analysis", className="nav-link"),
+        dash.dcc.Link("Prediction", href="/prediction", className="nav-link")
+    ], className="navbar")
+])
+
+# ----------------------------#
+# Footer
+# ----------------------------#
+footer = html.Footer([
+    html.Div("© 2025 Breast Cancer Analysis | October Rose Theme", className="footer")
+])
+
+# ----------------------------#
+# Layout
+# ----------------------------#
+app.layout = html.Div([
+    header,
+    html.Div(page_container, className="main-container"),
+    footer
+])
+
+# ----------------------------#
+# Run
+# ----------------------------#
+if __name__ == "__main__":
+    app.run(debug=True)

assets/style.css

@@ -0,0 +1,128 @@
+/* ----------------- General body ----------------- */
+body {
+    font-family: 'Arial', sans-serif;
+    background-color: #fff0f5;  /* soft pink background */
+    margin: 0;
+    padding: 0;
+}
+
+/* ----------------- Header ----------------- */
+header {
+    width: 100%;
+    background: linear-gradient(90deg, #ff7eb9, #ff63a5, #ff1e56);
+    color: white;
+    padding: 1rem 0;
+    text-align: center;
+    font-size: 1.5rem;
+    font-weight: bold;
+    box-shadow: 0 6px 12px rgba(0,0,0,0.2); /* stronger shadow */
+}
+
+/* ----------------- Footer ----------------- */
+footer {
+    width: 100%;
+    background: linear-gradient(90deg, #ff1e56, #ff63a5, #ff7eb9);
+    color: white;
+    padding: 1rem 0;
+    text-align: center;
+    font-size: 0.9rem;
+    box-shadow: 0 -6px 12px rgba(0,0,0,0.2); /* stronger shadow */
+    position: relative;
+    bottom: 0;
+}
+
+/* ----------------- Main content container ----------------- */
+.main-container {
+    max-width: 1200px;
+    margin: 2rem auto;
+    padding-left: 2rem;
+    padding-right: 2rem;
+    background-color: #ffffff; /* white background for content */
+    border-radius: 12px;       /* rounded corners */
+    box-shadow: 0 8px 20px rgba(0,0,0,0.1); /* soft shadow for card-like effect */
+}
+
+/* ----------------- Navigation bar ----------------- */
+.navbar {
+    display: flex;
+    justify-content: center;
+    gap: 2rem;
+    margin-top: 1rem;
+}
+.nav-link {
+    color: white !important;
+    font-weight: bold;
+    font-size: 1rem;
+    text-decoration: none;
+    transition: 0.3s;
+}
+.nav-link:hover {
+    text-decoration: underline;
+    text-shadow: 0 0 8px rgba(255,255,255,0.7); /* subtle glow on hover */
+}
+
+/* Page title */
+.page-title {
+    font-size: 32px;
+    font-weight: bold;
+    margin-bottom: 25px;
+    background: linear-gradient(to right, #ff77b4, #ff3c8c);
+    -webkit-background-clip: text;
+    color: transparent;
+}
+
+/* Card styling */
+.custom-card {
+    border-radius: 12px;
+    box-shadow: 0px 4px 15px rgba(255, 105, 180, 0.25);
+    border: none;
+}
+
+.card-header {
+    font-weight: 600;
+    background: linear-gradient(to right, #ffd1e8, #ffc0df);
+    border-radius: 12px 12px 0 0;
+}
+
+/* Dropdown styling */
+.dropdown {
+    box-shadow: 0px 2px 10px rgba(255, 105, 180, 0.2);
+}
+
+/* General text style */
+.filter-label {
+    font-weight: 600;
+}
+
+/* Page title */
+.page-title {
+    font-size: 32px;
+    font-weight: bold;
+    margin-bottom: 25px;
+    background: linear-gradient(to right, #ff77b4, #ff3c8c);
+    -webkit-background-clip: text;
+    color: transparent;
+}
+
+/* Card styling */
+.custom-card {
+    border-radius: 12px;
+    box-shadow: 0px 4px 15px rgba(255, 105, 180, 0.25);
+    border: none;
+}
+
+.card-header {
+    font-weight: 600;
+    background: linear-gradient(to right, #ffd1e8, #ffc0df);
+    border-radius: 12px 12px 0 0;
+}
+
+/* Dropdown styling */
+.dropdown {
+    box-shadow: 0px 2px 10px rgba(255, 105, 180, 0.2);
+}
+
+/* General text style */
+.filter-label {
+    font-weight: 600;
+}

pages/data_analysis.py

@@ -0,0 +1,187 @@
+import dash
+from dash import html, dcc, Input, Output
+import dash_bootstrap_components as dbc
+import plotly.express as px
+import pandas as pd
+from sklearn.datasets import load_breast_cancer
+
+dash.register_page(__name__, path="/data-analysis", name="Data Analysis")
+
+# --------------------------------------------
+# Load dataset
+# --------------------------------------------
+data = load_breast_cancer()
+df = pd.DataFrame(data.data, columns=data.feature_names)
+df["target"] = data.target
+df["target_label"] = df["target"].map({0: "Malignant", 1: "Benign"})
+
+# Important features
+important_features = [
+    "texture error", "area error", "smoothness error",
+    "concavity error", "symmetry error",
+    "fractal dimension error", "worst concavity"
+]
+top4_features = important_features[:4]  # For pairplots
+
+# --------------------------------------------
+# Layout
+# --------------------------------------------
+layout = html.Div(
+    style={"padding": "30px"},
+    children=[
+        html.H2("Data Analysis", className="page-title"),
+
+        # Filters row
+        dbc.Row(
+            [
+                dbc.Col(
+                    dcc.Dropdown(
+                        id="diagnosis-filter",
+                        options=[
+                            {"label": "All", "value": "all"},
+                            {"label": "Benign", "value": 1},
+                            {"label": "Malignant", "value": 0},
+                        ],
+                        value="all",
+                        clearable=False,
+                        placeholder="Filter by Diagnosis",
+                        style={
+                            "background": "linear-gradient(135deg, #ff77b4, #e61227)",
+                            "color": "#fff",
+                            "border-radius": "8px",
+                            "padding": "5px"
+                        }
+                    ),
+                    width=3
+                ),
+                dbc.Col(
+                    dcc.Dropdown(
+                        id="feature-select",
+                        options=[{"label": f, "value": f} for f in important_features],
+                        value=important_features[0],
+                        clearable=False,
+                        placeholder="Select Feature",
+                        style={
+                            "background": "linear-gradient(135deg, #ff77b4, #e61227)",
+                            "color": "#fff",
+                            "border-radius": "8px",
+                            "padding": "5px"
+                        }
+                    ),
+                    width=3
+                )
+            ],
+            className="mb-4",
+            align="center",
+            justify="start",
+            style={"gap": "20px"}
+        ),
+
+        # Heatmap Card
+        dbc.Card(
+            dbc.CardBody(dcc.Graph(id="heatmap-plot")),
+            className="custom-card shadow mb-4"
+        ),
+
+        # Pairplot Cards for top 4 features (2x2 grid)
+        dbc.Row(
+            [
+                dbc.Col(dcc.Graph(id=f"pairplot-{i}"), md=6)
+                for i in range(6)  # 6 combinations for 4 features
+            ],
+            className="mb-4",
+        ),
+
+        # Box Plot Card
+        dbc.Card(
+            dbc.CardBody(dcc.Graph(id="box-plot")),
+            className="custom-card shadow mb-4"
+        ),
+
+        # Violin Plot Card
+        dbc.Card(
+            dbc.CardBody(dcc.Graph(id="violin-plot")),
+            className="custom-card shadow mb-4"
+        ),
+
+        # Histogram Card
+        dbc.Card(
+            dbc.CardBody(dcc.Graph(id="histogram-plot")),
+            className="custom-card shadow mb-4"
+        ),
+    ]
+)
+
+# --------------------------------------------
+# Callbacks
+# --------------------------------------------
+from dash import callback
+
+@callback(
+    Output("heatmap-plot", "figure"),
+    [Output(f"pairplot-{i}", "figure") for i in range(6)],
+    Output("box-plot", "figure"),
+    Output("violin-plot", "figure"),
+    Output("histogram-plot", "figure"),
+    Input("diagnosis-filter", "value"),
+    Input("feature-select", "value")
+)
+def update_plots(filter_value, selected_feature):
+    # Filter data
+    filtered = df.copy()
+    if filter_value != "all":
+        filtered = filtered[filtered["target"] == filter_value]
+
+    # Heatmap
+    corr = filtered[important_features].corr()
+    fig_heatmap = px.imshow(corr, color_continuous_scale="RdPu")
+
+    # Pairplots (all pairs of top 4 features)
+    from itertools import combinations
+    pair_figs = []
+    for f1, f2 in combinations(top4_features, 2):
+        fig = px.scatter(
+            filtered,
+            x=f1,
+            y=f2,
+            color="target_label",
+            color_discrete_map={"Benign": "#ff77b4", "Malignant": "#9c005d"},
+        )
+        fig.update_layout(
+            xaxis_tickangle=45,
+            yaxis_tickangle=0,
+            margin=dict(l=40, r=20, t=20, b=40),
+        )
+        pair_figs.append(fig)
+
+    # Box plot
+    fig_box = px.box(
+        filtered,
+        y=selected_feature,
+        color="target_label",
+        color_discrete_map={"Benign": "#ff77b4", "Malignant": "#9c005d"},
+        points="all"
+    )
+
+    # Violin plot
+    fig_violin = px.violin(
+        filtered,
+        y=selected_feature,
+        color="target_label",
+        color_discrete_map={"Benign": "#ff77b4", "Malignant": "#9c005d"},
+        box=True,
+        points="all"
+    )
+
+    # Histogram plot
+    fig_hist = px.histogram(
+        filtered,
+        x=selected_feature,
+        color="target_label",
+        barmode="overlay",
+        opacity=0.7,
+        color_discrete_map={"Benign": "#ff77b4", "Malignant": "#9c005d"}
+    )
+
+    return fig_heatmap, *pair_figs, fig_box, fig_violin, fig_hist
+

pages/introduction.py

@@ -0,0 +1,157 @@
+import dash
+from dash import html, dcc
+from dash import dash_table
+import pandas as pd
+
+dash.register_page(__name__, path="/", name="Introduction")
+
+# -------------------------------------------------------------
+#  Summary text of original paper
+# -------------------------------------------------------------
+paper_summary = """
+The Breast Cancer Wisconsin Diagnostic dataset originates from the work of
+W. Nick Street, William H. Wolberg, and O. L. Mangasarian (1992). Their study
+introduced an automated system for classifying breast tumors using
+fine-needle aspirated (FNA) cytology images. 
+
+The system extracted quantitative characteristics of cell nuclei — such as radius,
+texture, smoothness, concavity, and symmetry — using active contour models 
+(“snakes”) to trace boundaries of nuclei precisely. With these features, the authors 
+used linear-programming-based classifiers and achieved cross-validation accuracy 
+reaching **97%**, marking one of the earliest strong uses of machine learning in 
+medical diagnosis.
+"""
+
+# -------------------------------------------------------------
+# Feature table
+# -------------------------------------------------------------
+feature_table = pd.DataFrame({
+    "Feature Group": [
+        "Radius", "Texture", "Perimeter", "Area", "Smoothness",
+        "Compactness", "Concavity", "Concave Points",
+        "Symmetry", "Fractal Dimension"
+    ],
+    "Description": [
+        "Mean distance from center to perimeter",
+        "Variation in pixel intensity",
+        "Boundary length of the nucleus",
+        "Size of the cell nucleus",
+        "Local variation in radius",
+        "Perimeter² / area",
+        "Severity of concave regions",
+        "Number of concave contour portions",
+        "Nuclear symmetry",
+        "Irregularity of contour"
+    ]
+})
+
+# -------------------------------------------------------------
+# Component style helpers (consistent with your app theme)
+# -------------------------------------------------------------
+CARD_STYLE = {
+    "background": "white",
+    "padding": "25px",
+    "borderRadius": "12px",
+    "boxShadow": "0 4px 12px rgba(0,0,0,0.1)",
+    "marginBottom": "25px"
+}
+
+TITLE_STYLE = {
+    "fontSize": "26px",
+    "fontWeight": "600",
+    "marginBottom": "15px",
+    "color": "#333"
+}
+
+TEXT_STYLE = {
+    "fontSize": "17px",
+    "lineHeight": "1.6",
+    "textAlign": "justify",
+    "color": "#444"
+}
+
+# -------------------------------------------------------------
+# Introduction Page Layout
+# -------------------------------------------------------------
+layout = html.Div(
+    style={
+        "maxWidth": "950px",
+        "margin": "auto",
+        "padding": "30px"
+    },
+    children=[
+
+        # -----------------------
+        # Title card
+        # -----------------------
+        html.Div(
+            style=CARD_STYLE,
+            children=[
+                html.H2("Introduction", style=TITLE_STYLE),
+                html.P(paper_summary, style=TEXT_STYLE)
+            ]
+        ),
+
+        # -----------------------
+        # Image Card
+        # -----------------------
+        html.Div(
+            style=CARD_STYLE,
+            children=[
+                html.Img(
+                    src="/assets/celltumor.PNG",
+                    style={
+                        "width": "100%",
+                        "borderRadius": "10px",
+                        "boxShadow": "0 2px 10px rgba(0,0,0,0.15)"
+                    }
+                ),
+                html.P(
+                    "Figure: Example of cell nuclei boundaries from the original study.",
+                    style={"textAlign": "center", "fontStyle": "italic", "marginTop": "10px"}
+                )
+            ]
+        ),
+
+        # -----------------------
+        # Dataset info card
+        # -----------------------
+        html.Div(
+            style=CARD_STYLE,
+            children=[
+                html.H3("Dataset Overview", style=TITLE_STYLE),
+                html.P(
+                    """
+                    The Breast Cancer Wisconsin Diagnostic dataset contains 569 samples 
+                    describing malignant and benign tumors. Each sample includes 30 numerical 
+                    features derived from nuclear characteristics. The values are computed as:
+                    mean, standard error, and “worst case” (largest) measures.
+                    """,
+                    style=TEXT_STYLE
+                ),
+
+                dash_table.DataTable(
+                    data=feature_table.to_dict('records'),
+                    columns=[{"name": col, "id": col} for col in feature_table.columns],
+                    style_cell={
+                        "fontSize": "16px",
+                        "padding": "8px",
+                        "textAlign": "left"
+                    },
+                    style_header={
+                        "backgroundColor": "#fafafa",
+                        "fontWeight": "600",
+                        "fontSize": "17px",
+                        "borderBottom": "1px solid #ddd"
+                    },
+                    style_table={
+                        "marginTop": "20px",
+                        "boxShadow": "0 2px 8px rgba(0,0,0,0.1)",
+                        "borderRadius": "8px",
+                        "overflow": "hidden"
+                    }
+                )
+            ]
+        )
+    ]
+)

pages/prediction.py

@@ -0,0 +1,175 @@
+import os
+import joblib
+import numpy as np
+import pandas as pd
+import plotly.express as px
+import plotly.graph_objects as go
+from sklearn.metrics import roc_curve, roc_auc_score, confusion_matrix
+
+import dash
+from dash import html, dcc, Input, Output, State
+import dash_bootstrap_components as dbc
+
+dash.register_page(__name__, path="/prediction", name="Prediction")
+
+# ----------------------------
+# Paths
+# ----------------------------
+BASE_DIR = os.path.dirname(__file__)
+MODEL_PATH = os.path.join(BASE_DIR, "saved_models", "logreg_breastcancer_reduced.pkl")
+TRAIN_PATH = os.path.join(BASE_DIR, "saved_models", "X_train_y_train.csv")
+
+# ----------------------------
+# Load model and training data
+# ----------------------------
+if os.path.exists(MODEL_PATH):
+    model = joblib.load(MODEL_PATH)
+else:
+    raise FileNotFoundError(f"Model file not found at {MODEL_PATH}")
+
+if os.path.exists(TRAIN_PATH):
+    train_data = pd.read_csv(TRAIN_PATH)
+else:
+    raise FileNotFoundError(f"Training data CSV not found at {TRAIN_PATH}")
+
+# ----------------------------
+# Features used in model
+# ----------------------------
+features = [
+    'texture error', 'area error', 'smoothness error', 'concavity error',
+    'symmetry error', 'fractal dimension error', 'worst concavity'
+]
+
+feature_labels = [
+    "Texture Error", "Area Error", "Smoothness Error", "Concavity Error",
+    "Symmetry Error", "Fractal Dimension Error", "Worst Concavity"
+]
+
+X_train = train_data[features]
+y_train = train_data['target']
+
+# ----------------------------
+# Precompute performance plots
+# ----------------------------
+y_proba_train = model.predict_proba(X_train)[:, 1]
+y_pred_train = model.predict(X_train)
+
+# ROC Curve
+fpr, tpr, _ = roc_curve(y_train, y_proba_train)
+auc_score = roc_auc_score(y_train, y_proba_train)
+fig_roc = go.Figure()
+fig_roc.add_trace(go.Scatter(x=fpr, y=tpr, mode='lines', line=dict(color="#e61227", width=3), name=f"AUC={auc_score:.3f}"))
+fig_roc.add_trace(go.Scatter(x=[0, 1], y=[0, 1], mode='lines', line=dict(color="gray", dash="dash")))
+fig_roc.update_layout(title="ROC Curve", margin=dict(l=20, r=20, t=40, b=20))
+
+# Feature importance
+clf = model.named_steps[list(model.named_steps.keys())[-1]]
+if hasattr(clf, "coef_"):
+    coefs = clf.coef_.ravel()
+    fig_feat = px.bar(x=features, y=coefs, color=coefs, color_continuous_scale="RdPu", title="Feature Importance")
+    fig_feat.update_layout(margin=dict(l=20, r=20, t=40, b=20))
+else:
+    fig_feat = go.Figure()
+
+# Confusion Matrix
+cm = confusion_matrix(y_train, y_pred_train)
+fig_cm = go.Figure(data=go.Heatmap(z=cm, x=["Pred Malignant (0)", "Pred Benign (1)"], y=["Actual Malignant (0)", "Actual Benign (1)"], colorscale="RdPu", showscale=False))
+fig_cm.update_layout(title="Confusion Matrix", margin=dict(l=20, r=20, t=40, b=20))
+
+# ----------------------------
+# Layout
+# ----------------------------
+layout = html.Div([
+    html.H2("Breast Cancer Prediction", style={"margin-bottom": "30px"}),
+
+    dbc.Card(
+        dbc.CardBody([
+            dbc.Row([
+                dbc.Col([
+                    html.Label(label),
+                    dbc.Input(id=f"input-{feat}", type="number", step=0.0001, value=0)
+                ], width=3, className="mb-2")
+                for feat, label in zip(features, feature_labels)
+            ], className="mb-3"),
+            dbc.Button("Run Diagnostic Prediction", id="predict-btn", color="light", className="mb-3"),
+            html.Div(id="prediction-output")
+        ]),
+        style={
+            "background": "linear-gradient(135deg, #ff77b4, #e61227)",
+            "color": "#fff",
+            "box-shadow": "0 4px 15px rgba(0,0,0,0.2)",
+            "padding": "20px",
+            "border-radius": "10px",
+            "margin-bottom": "40px"
+        }
+    ),
+
+    dbc.Card(
+        dbc.CardBody([
+            dbc.Row([
+                dbc.Col(dcc.Graph(figure=fig_roc), md=4),
+                dbc.Col(dcc.Graph(figure=fig_feat), md=4),
+                dbc.Col(dcc.Graph(figure=fig_cm), md=4),
+            ])
+        ])
+    )
+], style={"margin": "20px 3%"})
+
+# ----------------------------
+# Callback for user prediction
+# ----------------------------
+@dash.callback(
+    Output("prediction-output", "children"),
+    Input("predict-btn", "n_clicks"),
+    [State(f"input-{feat}", "value") for feat in features]
+)
+def predict_user(n_clicks, *vals):
+    if n_clicks is None:
+        return ""
+
+    # Sanitize inputs (The Bug Fix)
+    cleaned_vals = [float(v) if v is not None else 0.0 for v in vals]
+
+    try:
+        x_input = pd.DataFrame([cleaned_vals], columns=features)
+        
+        # Get binary prediction (0 or 1)
+        y_pred = model.predict(x_input)[0]
+        
+        # Get probabilities for both classes
+        # probas[0] is for class 0 (Malignant), probas[1] is for class 1 (Benign)
+        probas = model.predict_proba(x_input)[0]
+        prob_malignant = probas[0]
+        prob_benign = probas[1]
+
+        # Determine label based on Jupyter logic (0=Malignant, 1=Benign)
+        if y_pred == 0:
+            result_text = "MALIGNANT"
+            result_color = "#FFD700" # Warning Gold
+            badge_color = "danger"
+        else:
+            result_text = "BENIGN"
+            result_color = "#00FF7F" # Spring Green
+            badge_color = "success"
+
+        return html.Div([
+            html.Hr(style={"borderTop": "1px solid white"}),
+            html.H3([
+                f"Model Classification: ",
+                dbc.Badge(result_text, color=badge_color, className="ms-2")
+            ], style={"fontWeight": "bold"}),
+            
+            dbc.Row([
+                dbc.Col([
+                    html.P(f"Probability of Malignant (Class 0): {prob_malignant:.2%}"),
+                    dbc.Progress(value=prob_malignant*100, color="dark", style={"height": "10px"})
+                ], md=6),
+                dbc.Col([
+                    html.P(f"Probability of Benign (Class 1): {prob_benign:.2%}"),
+                    dbc.Progress(value=prob_benign*100, color="info", style={"height": "10px"})
+                ], md=6),
+            ], className="mt-3")
+        ], style={"color": "white"})
+
+    except Exception as e:
+        return html.Div(f"Prediction Error: {e}", style={"color": "white", "background": "red", "padding": "10px"})

pages/saved_models/X_train_y_train.csv

@@ -0,0 +1,456 @@
+texture error,area error,smoothness error,concavity error,symmetry error,fractal dimension error,worst concavity,target
+0.967,12.97,0.007086,0.01012,0.0156,0.002606,0.04384,1
+1.001,52.49,0.009087,0.05546,0.02451,0.004005,0.5308,0
+1.925,21.98,0.008713,0.0,0.03265,0.001002,0.0,1
+0.4981,21.03,0.005851,0.02544,0.01842,0.002918,0.2577,1
+1.974,17.49,0.006538,0.01376,0.03416,0.002928,0.07529,1
+1.909,39.43,0.00579,0.05303,0.03356,0.009368,0.25,1
+0.9112,20.52,0.005356,0.01971,0.01414,0.001892,0.1472,1
+4.885,21.69,0.001713,0.0,0.03799,0.001688,0.0,1
+0.9789,16.94,0.01835,0.09263,0.02384,0.005601,0.1544,1
+0.6237,37.11,0.004953,0.03035,0.01539,0.002281,0.2492,1
+1.038,18.62,0.006662,0.02105,0.01677,0.002784,0.1804,1
+0.4334,23.31,0.003271,0.0231,0.01148,0.002379,0.3151,1
+0.5914,18.52,0.005367,0.03049,0.01377,0.003187,0.503,0
+1.152,18.02,0.00718,0.005832,0.01982,0.002754,0.04506,1
+0.8737,59.7,0.005089,0.03052,0.01057,0.003391,0.4185,0
+0.6417,13.04,0.006982,0.04017,0.0226,0.006822,0.269,1
+1.012,43.5,0.005233,0.03576,0.01768,0.002967,0.6335,0
+1.908,21.38,0.006664,0.01158,0.02282,0.003526,0.07708,1
+0.8568,33.63,0.004757,0.02332,0.01394,0.002362,0.3378,0
+0.6999,130.2,0.003978,0.03576,0.01518,0.003796,0.4756,0
+0.8265,20.53,0.00328,0.0139,0.0138,0.001286,0.2085,0
+2.878,25.17,0.01474,0.01367,0.03044,0.00459,0.06141,1
+1.108,22.77,0.007356,0.05915,0.02165,0.004784,0.1648,1
+1.736,100.4,0.004938,0.04093,0.02816,0.002719,0.3092,0
+1.05,26.65,0.0058,0.007816,0.02734,0.003114,0.03122,1
+1.057,39.93,0.004351,0.03371,0.02598,0.003087,0.1359,1
+0.3981,29.06,0.004732,0.01855,0.02163,0.002783,0.2151,1
+0.9053,153.4,0.006399,0.05373,0.03003,0.006193,0.7119,0
+2.342,14.16,0.004352,0.01343,0.02671,0.001777,0.04833,1
+1.336,28.51,0.004449,0.03312,0.01906,0.004015,0.3114,1
+1.13,19.63,0.01546,0.02197,0.03997,0.003901,0.09996,1
+0.9004,139.9,0.004989,0.03571,0.01879,0.00476,0.4658,0
+0.8732,18.33,0.007962,0.01585,0.02254,0.001906,0.1039,1
+1.042,16.57,0.00591,0.01902,0.01202,0.003107,0.1791,1
+1.667,58.53,0.03113,0.1438,0.02175,0.01256,0.2803,0
+1.332,74.08,0.00677,0.03067,0.01875,0.003434,0.2802,0
+0.8509,153.1,0.006369,0.04266,0.02335,0.003385,0.6451,0
+1.108,19.54,0.004242,0.06578,0.01638,0.004406,0.3662,1
+0.7747,41.51,0.007159,0.06165,0.01591,0.005099,0.9034,0
+1.268,37.83,0.008034,0.01514,0.02921,0.002005,0.06735,1
+1.095,20.35,0.005293,0.02071,0.01748,0.002848,0.1731,1
+2.927,29.11,0.01159,0.0,0.03004,0.003324,0.0,1
+0.5679,22.95,0.002667,0.01423,0.01961,0.0017,0.2477,0
+0.7884,27.4,0.007295,0.04615,0.01561,0.00323,0.4504,1
+0.8902,27.19,0.00751,0.03672,0.02165,0.005082,0.5355,0
+1.748,53.65,0.004571,0.02176,0.03373,0.005875,0.05186,1
+0.7693,26.5,0.00591,0.007066,0.02223,0.002378,0.07127,1
+1.851,26.85,0.008005,0.03321,0.01462,0.004452,0.3194,0
+1.217,15.05,0.007899,0.008534,0.02637,0.003761,0.06572,1
+0.7383,45.42,0.004493,0.02048,0.01144,0.001575,0.3889,0
+1.679,58.38,0.008109,0.04942,0.01594,0.003739,0.5036,0
+1.268,60.78,0.009407,0.06899,0.017,0.006113,0.6922,0
+1.016,12.96,0.006794,0.0398,0.02134,0.004603,0.4858,1
+0.7886,23.56,0.008462,0.02387,0.0198,0.0023,0.239,1
+0.7614,18.54,0.006142,0.001835,0.01637,0.002665,0.01854,1
+1.15,14.91,0.004942,0.007508,0.01442,0.001684,0.07934,1
+1.222,11.77,0.009058,0.03029,0.01609,0.00357,0.2644,1
+1.305,76.36,0.00553,0.0611,0.0214,0.005036,0.2535,0
+1.563,21.46,0.008872,0.05946,0.02793,0.004775,0.2806,1
+0.9223,15.09,0.005251,0.02526,0.02514,0.004198,0.3162,1
+1.493,16.64,0.007189,0.01081,0.02158,0.002619,0.1125,1
+0.6218,23.12,0.003728,0.01988,0.01647,0.00197,0.1091,1
+1.041,69.47,0.00582,0.04252,0.01527,0.006299,0.6566,0
+1.207,30.19,0.007234,0.1114,0.03232,0.009627,0.4896,1
+0.6538,25.03,0.01017,0.02789,0.03127,0.009423,0.0942,1
+1.083,9.332,0.0042,0.003846,0.01487,0.002295,0.02533,1
+1.617,199.7,0.004551,0.02143,0.01367,0.002299,0.3442,0
+1.046,32.74,0.007976,0.01608,0.02005,0.00283,0.1117,1
+0.5391,15.75,0.006153,0.01693,0.01651,0.002551,0.1922,1
+1.627,45.38,0.006831,0.02489,0.03151,0.00175,0.1547,0
+1.069,25.13,0.006983,0.04683,0.0168,0.005617,0.6282,0
+0.6124,13.22,0.004394,0.01451,0.01291,0.002074,0.1364,1
+1.025,19.68,0.004854,0.01826,0.01386,0.002304,0.1703,1
+0.7869,94.03,0.00615,0.03832,0.0225,0.004571,0.4504,0
+0.9768,15.7,0.009606,0.01985,0.02027,0.002968,0.08867,1
+2.174,24.62,0.01037,0.02586,0.01816,0.003976,0.1755,1
+1.142,14.34,0.003418,0.001595,0.01613,0.0009683,0.007977,1
+0.6674,13.32,0.003888,0.01256,0.01608,0.001638,0.1887,1
+1.023,7.326,0.01027,0.02613,0.02277,0.00589,0.1783,1
+1.892,103.6,0.008439,0.05904,0.0371,0.004286,0.3703,0
+1.278,23.02,0.005345,0.02889,0.009947,0.003359,0.5703,0
+1.147,43.4,0.006003,0.02151,0.0152,0.001868,0.2644,0
+1.4,93.91,0.009037,0.05206,0.01778,0.004968,0.3583,0
+1.633,90.94,0.006717,0.04638,0.02747,0.005838,0.2298,0
+0.9861,16.41,0.009113,0.02443,0.01568,0.002477,0.312,1
+1.86,19.91,0.01188,0.04591,0.02287,0.006792,0.1295,1
+0.7096,44.91,0.006789,0.06446,0.03672,0.004394,0.6305,0
+1.026,118.8,0.006399,0.07845,0.02057,0.006213,0.6599,0
+1.341,11.6,0.005724,0.002074,0.01445,0.002411,0.01235,1
+1.474,120.0,0.008166,0.0573,0.01065,0.005893,0.6476,0
+1.479,11.73,0.01547,0.09252,0.02105,0.007551,0.3393,1
+1.199,63.33,0.005033,0.04755,0.01578,0.003224,0.5673,0
+2.509,19.33,0.01736,0.02611,0.03675,0.006758,0.07162,1
+1.284,31.59,0.006627,0.05371,0.01682,0.004584,0.5862,0
+0.5293,13.17,0.006472,0.01282,0.01692,0.002817,0.1275,1
+0.6793,7.254,0.007897,0.01801,0.01592,0.003925,0.1754,1
+0.6881,12.98,0.004259,0.0194,0.01191,0.003537,0.2079,1
+1.48,111.7,0.008124,0.05489,0.03176,0.002365,0.3861,0
+1.44,20.3,0.007278,0.04447,0.01868,0.003339,0.256,1
+1.845,31.0,0.01088,0.03688,0.04499,0.004768,0.3744,0
+1.924,28.93,0.005841,0.007936,0.01564,0.002985,0.07003,1
+0.9238,34.66,0.007162,0.05473,0.01547,0.007098,0.6376,0
+1.194,17.67,0.009549,0.3038,0.04197,0.009559,1.252,1
+1.324,51.22,0.009329,0.09953,0.05543,0.00733,0.6872,0
+0.7873,11.36,0.009172,0.0,0.02711,0.003399,0.0,1
+1.35,22.45,0.006383,0.00186,0.02571,0.002015,0.005579,1
+0.9086,15.75,0.005298,0.02321,0.01853,0.002152,0.1764,1
+1.352,156.8,0.005687,0.06329,0.01924,0.004614,0.5807,0
+1.14,14.66,0.005919,0.04957,0.01208,0.004076,0.3308,1
+0.905,11.36,0.002887,0.01613,0.0187,0.001972,0.181,1
+0.7372,42.76,0.005508,0.04436,0.02427,0.004841,0.2604,1
+1.466,105.0,0.006248,0.05196,0.02007,0.00456,0.6133,0
+0.7629,81.46,0.004253,0.03872,0.01798,0.005295,0.678,0
+1.851,18.54,0.006113,0.04645,0.01451,0.003756,0.4234,0
+0.8522,25.44,0.01721,0.05671,0.02541,0.02193,0.1434,1
+1.143,20.56,0.01017,0.01861,0.03464,0.001971,0.04158,1
+0.504,18.54,0.007327,0.01798,0.01962,0.002234,0.1622,1
+0.9644,47.14,0.00925,0.04867,0.01498,0.00352,0.5203,0
+0.976,111.4,0.008029,0.03732,0.02308,0.007444,0.3853,0
+1.907,30.66,0.006587,0.01737,0.01835,0.002318,0.1366,1
+1.166,22.22,0.003741,0.01065,0.01344,0.001126,0.106,1
+1.502,20.95,0.007112,0.02703,0.01958,0.004463,0.2434,1
+0.8355,18.32,0.005996,0.02117,0.02025,0.001725,0.1423,1
+0.8561,49.0,0.00486,0.02602,0.01226,0.002759,0.3241,0
+0.7712,16.64,0.005324,0.0151,0.02104,0.001887,0.209,1
+0.9533,18.85,0.005314,0.02185,0.01223,0.002846,0.4069,0
+1.022,45.5,0.005635,0.06072,0.03197,0.004085,0.7087,0
+1.285,17.26,0.005608,0.01529,0.01909,0.002133,0.1255,1
+0.9245,164.1,0.006292,0.03582,0.01479,0.003118,0.4819,0
+1.678,18.99,0.006908,0.006972,0.02694,0.00206,0.03582,1
+1.21,28.47,0.005857,0.01168,0.02406,0.001769,0.05523,1
+0.9938,12.67,0.005133,0.01434,0.01501,0.001588,0.1399,1
+0.828,36.74,0.007571,0.02623,0.0193,0.001676,0.221,0
+1.299,20.21,0.003629,0.03452,0.02632,0.003705,0.1604,1
+1.336,31.24,0.005868,0.02021,0.02087,0.002583,0.1049,1
+1.281,35.24,0.006703,0.02315,0.019,0.003224,0.3024,0
+2.508,34.37,0.006578,0.02662,0.01359,0.003707,0.1046,1
+1.033,32.55,0.005607,0.04741,0.01857,0.005466,0.7026,0
+2.043,20.05,0.01113,0.005308,0.01801,0.005667,0.02049,1
+0.9264,28.41,0.003704,0.0153,0.01062,0.002217,0.1673,1
+1.017,112.4,0.006494,0.03391,0.01356,0.001997,0.5372,0
+0.5733,12.84,0.00445,0.01334,0.01698,0.002787,0.1848,1
+0.8225,10.8,0.007416,0.02758,0.02348,0.002917,0.2299,1
+1.433,45.81,0.005444,0.01622,0.01419,0.002751,0.208,0
+1.532,13.24,0.007881,0.007004,0.01939,0.002222,0.03619,1
+1.462,19.14,0.01266,0.0,0.02882,0.006872,0.0,1
+0.9505,17.61,0.006809,0.01329,0.02057,0.001784,0.102,1
+1.452,101.9,0.01,0.06577,0.05168,0.002887,0.3355,0
+1.786,18.21,0.006122,0.01596,0.03194,0.002211,0.07239,1
+0.8339,29.91,0.004675,0.01603,0.01095,0.001629,0.2712,0
+1.018,31.01,0.004107,0.02821,0.0161,0.002744,0.2512,1
+1.747,43.52,0.01307,0.006021,0.031,0.004225,0.02085,1
+0.6724,26.03,0.006583,0.005949,0.02216,0.002668,0.03046,1
+3.12,233.0,0.02333,0.1278,0.04547,0.009875,0.5803,0
+1.214,54.04,0.004024,0.02291,0.05014,0.001902,0.2249,0
+0.7927,22.79,0.008584,0.03047,0.02769,0.003479,0.3009,1
+0.6745,9.006,0.003265,0.006493,0.0172,0.00136,0.06243,1
+0.9197,45.19,0.005776,0.03695,0.02789,0.002665,0.5409,0
+1.555,13.66,0.005391,0.01163,0.01341,0.001659,0.1811,1
+0.9591,23.47,0.008328,0.01349,0.03218,0.002386,0.09076,1
+1.743,130.8,0.007964,0.07649,0.02736,0.005928,0.4932,0
+0.8135,23.81,0.004929,0.07683,0.01526,0.008133,0.6556,1
+1.803,20.48,0.01291,0.05101,0.02144,0.005891,0.2216,1
+0.7786,18.57,0.005833,0.02,0.01938,0.00196,0.2413,1
+2.11,31.72,0.00797,0.1166,0.05113,0.01172,0.8488,0
+2.324,29.96,0.006307,0.0385,0.01185,0.003589,0.3064,1
+0.7732,53.91,0.004314,0.02254,0.01369,0.002179,0.3784,0
+0.6583,44.64,0.005393,0.04303,0.01792,0.004168,0.583,0
+1.375,56.18,0.0119,0.04907,0.01641,0.001807,0.3977,0
+0.8208,137.9,0.005283,0.09518,0.02401,0.005002,0.6991,0
+0.6931,13.38,0.006064,0.006564,0.01374,0.001392,0.05233,1
+0.9951,53.16,0.005654,0.03059,0.01623,0.001965,0.4316,0
+0.8937,24.25,0.006532,0.02905,0.01743,0.003643,0.5006,0
+1.354,23.04,0.004147,0.03379,0.01394,0.002327,0.3779,1
+0.8554,68.46,0.005038,0.01946,0.02294,0.002581,0.1932,0
+1.232,21.19,0.006054,0.005681,0.01215,0.001514,0.04462,1
+1.962,10.21,0.01243,0.07753,0.02309,0.01178,0.5381,1
+1.217,24.28,0.00508,0.007276,0.0135,0.001706,0.06648,1
+1.39,17.67,0.02177,0.05189,0.02632,0.01148,0.2913,1
+0.4833,29.34,0.006432,0.007741,0.01227,0.002564,0.03517,1
+0.5796,8.322,0.01011,0.01981,0.0209,0.002788,0.1168,1
+2.643,44.96,0.007517,0.01465,0.02047,0.003883,0.05524,1
+0.3602,9.438,0.004124,0.01003,0.02032,0.001952,0.08324,1
+1.647,15.46,0.004359,0.003223,0.01916,0.002534,0.02318,1
+1.367,18.76,0.008835,0.01328,0.01897,0.001726,0.08653,1
+1.885,116.4,0.01038,0.1091,0.07895,0.005987,0.7681,0
+1.111,33.76,0.004868,0.01121,0.02085,0.002893,0.09189,1
+0.6221,19.75,0.004796,0.01758,0.02254,0.001971,0.206,1
+0.8098,35.74,0.006351,0.03119,0.02062,0.002695,0.3209,0
+0.8745,15.34,0.005251,0.0184,0.01449,0.002671,0.2758,1
+1.38,19.87,0.007499,0.02332,0.01647,0.002629,0.2177,0
+1.239,17.74,0.006547,0.02018,0.01671,0.00236,0.09755,1
+2.06,46.61,0.003443,0.03056,0.0152,0.001519,0.1882,1
+1.685,12.67,0.005371,0.01132,0.01719,0.001444,0.0846,1
+2.836,70.1,0.01124,0.07469,0.02768,0.00624,0.3829,0
+0.5864,8.966,0.008261,0.03259,0.01708,0.003806,0.2456,1
+1.39,21.91,0.006719,0.04387,0.01872,0.008015,0.2365,1
+1.194,22.69,0.00596,0.03909,0.01939,0.00456,0.4636,0
+1.377,50.96,0.008805,0.02488,0.01486,0.005412,0.2678,0
+2.612,23.22,0.01604,0.01865,0.03476,0.00356,0.1181,1
+1.001,69.65,0.007392,0.03988,0.01435,0.003446,0.5754,0
+0.7815,15.48,0.009019,0.01196,0.02388,0.001619,0.07116,1
+1.023,69.06,0.005485,0.0319,0.02768,0.003345,0.5344,0
+2.542,13.12,0.01072,0.01993,0.01717,0.004492,0.03986,1
+1.35,17.58,0.005768,0.0151,0.01347,0.001828,0.139,1
+0.9849,54.16,0.005771,0.02791,0.02008,0.004144,0.3965,0
+0.9823,16.51,0.005518,0.01994,0.01799,0.002484,0.1943,1
+0.8907,24.68,0.006032,0.02259,0.01482,0.002496,0.1786,1
+2.067,18.39,0.01193,0.03,0.03357,0.003048,0.09001,1
+0.8561,17.91,0.004599,0.009127,0.01247,0.001708,0.08115,1
+0.8944,9.227,0.003457,0.01167,0.01251,0.001356,0.1937,1
+1.047,23.12,0.006298,0.02615,0.0149,0.003599,0.1377,1
+0.7394,21.2,0.005706,0.03114,0.01454,0.002528,0.3103,1
+0.7198,10.77,0.003492,0.004826,0.01536,0.001381,0.03866,1
+1.511,24.44,0.005433,0.01131,0.0222,0.003408,0.0498,1
+2.105,49.11,0.005596,0.01272,0.01575,0.002758,0.0612,0
+0.7476,33.27,0.005839,0.03715,0.01467,0.003121,0.4956,0
+0.3871,13.87,0.006034,0.03336,0.01175,0.002256,0.4004,1
+0.7452,180.2,0.005753,0.03976,0.02201,0.002897,0.3794,0
+0.4801,17.25,0.003828,0.007078,0.01054,0.001697,0.1206,1
+0.9027,11.86,0.006513,0.002817,0.01502,0.002821,0.02639,1
+0.6232,20.72,0.006708,0.01482,0.0158,0.001779,0.1101,1
+0.9097,16.97,0.004729,0.001184,0.01466,0.001755,0.007732,1
+1.36,16.83,0.008412,0.03898,0.01695,0.002801,0.2439,1
+0.9527,28.3,0.005783,0.0007929,0.02043,0.001058,0.003581,1
+0.6857,35.03,0.004185,0.02664,0.01703,0.003817,0.5274,0
+2.079,28.85,0.01582,0.0,0.01865,0.006736,0.0,1
+0.78,92.81,0.008482,0.068,0.01467,0.007259,0.8489,0
+0.6575,77.02,0.006211,0.02681,0.01276,0.001711,0.4159,0
+0.7294,19.87,0.005488,0.02322,0.01428,0.002422,0.305,1
+1.656,21.55,0.01134,0.03125,0.01879,0.005348,0.1688,1
+2.015,16.85,0.007803,0.0169,0.021,0.002778,0.1055,1
+0.8249,31.33,0.005072,0.02185,0.01719,0.003317,0.3664,0
+0.8073,19.01,0.005403,0.01051,0.01333,0.002065,0.1167,1
+0.5762,14.03,0.003308,0.009904,0.01316,0.002095,0.1384,1
+0.5308,15.26,0.004271,0.02828,0.01461,0.002613,0.2866,1
+0.6633,71.56,0.006294,0.05554,0.02428,0.003535,0.7345,0
+1.139,18.04,0.005096,0.00941,0.01608,0.002399,0.123,1
+1.027,13.99,0.007405,0.04588,0.01738,0.004435,0.8402,0
+1.166,14.34,0.004957,0.04156,0.01843,0.003614,0.2596,1
+1.231,7.228,0.008499,0.1535,0.01617,0.0122,0.603,1
+0.9899,21.79,0.008534,0.00618,0.01065,0.003351,0.02758,1
+0.5735,15.5,0.003632,0.001128,0.01344,0.002585,0.0112,1
+2.454,138.5,0.01236,0.08232,0.02337,0.006042,0.6181,0
+1.361,81.89,0.005467,0.03185,0.01029,0.002205,0.4399,0
+1.798,41.24,0.006011,0.05175,0.02669,0.007731,0.1838,1
+1.478,27.49,0.009853,0.06271,0.02639,0.004205,0.2388,1
+0.7151,12.69,0.004928,0.00262,0.01393,0.001344,0.01938,1
+1.255,16.16,0.005969,0.02007,0.01972,0.002607,0.2267,1
+1.331,66.91,0.007269,0.04972,0.01852,0.004232,0.5553,0
+0.8749,24.19,0.006965,0.07926,0.01499,0.005784,0.9019,0
+1.467,17.85,0.003495,0.03445,0.02912,0.004723,0.1564,1
+1.74,27.85,0.01459,0.04961,0.01807,0.005217,0.3186,1
+1.666,104.9,0.006548,0.09723,0.05333,0.007646,0.7242,0
+0.4757,28.92,0.002866,0.01412,0.01069,0.001087,0.3538,0
+1.332,19.29,0.005442,0.03304,0.01315,0.002464,0.3438,1
+0.9078,30.15,0.007702,0.01307,0.0297,0.001432,0.04921,1
+2.011,14.2,0.01052,0.01714,0.02279,0.004237,0.09412,1
+1.019,24.91,0.005878,0.04815,0.02028,0.004022,0.5186,0
+0.9306,33.67,0.005414,0.03452,0.01705,0.004005,0.5106,0
+1.29,43.14,0.005872,0.02647,0.01465,0.002355,0.3169,0
+0.7656,12.89,0.006709,0.0208,0.02124,0.002768,0.186,1
+1.678,29.63,0.005836,0.005812,0.02014,0.002326,0.04753,1
+0.4064,11.48,0.007809,0.01099,0.01254,0.00212,0.1047,1
+0.7813,94.44,0.01149,0.05688,0.01756,0.005115,0.4,0
+1.01,18.19,0.008577,0.02099,0.02434,0.001217,0.1624,1
+0.9115,28.9,0.005031,0.005325,0.01494,0.0008948,0.04746,1
+1.28,17.09,0.008426,0.001487,0.02358,0.001627,0.004955,1
+0.8309,19.96,0.004405,0.04344,0.01921,0.004622,0.3076,1
+1.059,22.93,0.006652,0.02221,0.01894,0.003411,0.1226,1
+1.095,18.49,0.009702,0.02575,0.02801,0.00248,0.1889,1
+1.186,124.4,0.006804,0.03446,0.01897,0.004045,0.3617,0
+1.002,24.32,0.005731,0.03553,0.02143,0.003749,0.539,0
+1.434,9.549,0.005042,0.04305,0.0247,0.007358,0.2912,1
+2.188,106.0,0.006883,0.01818,0.007882,0.001754,0.02398,0
+1.554,20.24,0.006854,0.06663,0.02354,0.008925,0.3218,1
+1.03,41.0,0.005551,0.04205,0.02273,0.005667,0.6956,0
+1.048,97.07,0.004057,0.04029,0.01686,0.003318,0.681,0
+0.9489,41.18,0.006985,0.03011,0.01602,0.003884,0.4704,0
+0.8285,33.01,0.004148,0.002831,0.01422,0.002273,0.01824,1
+0.6656,17.43,0.008045,0.01683,0.01924,0.002248,0.1242,1
+0.8301,12.64,0.01164,0.01186,0.02383,0.00354,0.07161,1
+1.849,93.54,0.01075,0.05081,0.02293,0.004217,0.3446,0
+0.9961,15.07,0.005617,0.0009737,0.017,0.00203,0.005518,1
+1.189,70.01,0.00502,0.03457,0.01298,0.002887,0.4146,0
+0.8225,61.1,0.005627,0.03407,0.01925,0.003742,0.2489,0
+0.3628,20.0,0.004291,0.01841,0.009539,0.001656,0.2962,1
+1.202,68.35,0.006001,0.02855,0.01492,0.002205,0.3965,0
+1.04,28.32,0.00653,0.04712,0.0274,0.004651,0.1904,1
+0.7574,21.47,0.002838,0.0178,0.01329,0.001976,0.1564,1
+1.583,10.09,0.009501,0.04401,0.01322,0.003534,0.2123,1
+0.5503,48.9,0.004821,0.02408,0.01275,0.002451,0.3853,0
+2.664,49.85,0.01097,0.396,0.03546,0.02984,0.8216,1
+0.7959,12.58,0.006272,0.03966,0.0132,0.003813,0.3535,1
+1.268,26.43,0.01439,0.001597,0.02538,0.00347,0.00692,1
+2.463,99.04,0.005769,0.0395,0.01898,0.002498,0.3215,0
+0.8413,29.44,0.009882,0.04531,0.02471,0.002142,0.2846,0
+1.205,22.65,0.004625,0.07359,0.02137,0.006142,1.17,0
+0.9635,155.8,0.006428,0.04497,0.0159,0.003053,0.582,0
+0.6612,27.19,0.00647,0.0181,0.01898,0.001794,0.1533,1
+0.7615,12.25,0.009191,0.0094,0.01755,0.003009,0.09823,1
+0.7339,15.89,0.005884,0.02631,0.01848,0.001982,0.2302,1
+1.809,34.44,0.009098,0.03763,0.01878,0.005672,0.4425,0
+2.777,17.81,0.02075,0.0,0.06146,0.00682,0.0,1
+0.6329,17.47,0.00721,0.01311,0.01996,0.002635,0.09203,1
+0.4125,17.72,0.005012,0.01551,0.01647,0.001767,0.1362,1
+0.5477,11.88,0.005682,0.008496,0.01938,0.002371,0.08615,1
+1.219,18.24,0.005518,0.02589,0.02593,0.002157,0.1992,1
+1.471,22.68,0.01049,0.04004,0.02719,0.007596,0.1898,1
+1.198,38.49,0.004952,0.02967,0.01152,0.001718,0.2866,0
+1.19,16.26,0.004911,0.01397,0.01454,0.001858,0.162,1
+1.187,40.51,0.004029,0.01101,0.0146,0.003042,0.1459,0
+0.873,19.2,0.006715,0.04757,0.01838,0.006884,0.3206,1
+1.214,32.96,0.007491,0.000692,0.0219,0.00299,0.001845,1
+1.424,22.87,0.01385,0.02722,0.03281,0.004638,0.13,1
+0.9858,16.04,0.006635,0.02101,0.02108,0.003721,0.2247,1
+1.508,9.833,0.01019,0.0,0.02659,0.0041,0.0,1
+2.112,49.7,0.0138,0.04665,0.02689,0.004306,0.3809,0
+1.926,14.47,0.007831,0.01556,0.03139,0.001988,0.08803,1
+0.8155,27.94,0.005217,0.01678,0.01669,0.00233,0.1709,1
+1.781,25.79,0.005888,0.02059,0.02578,0.002267,0.1377,1
+0.9209,80.99,0.005215,0.04718,0.02045,0.004028,0.7053,0
+0.4706,20.67,0.007394,0.0247,0.01344,0.002569,0.1947,1
+1.005,19.83,0.004088,0.01796,0.01323,0.001465,0.3796,0
+1.072,58.63,0.008699,0.0595,0.01495,0.005984,0.7356,0
+1.693,38.34,0.009433,0.04167,0.03397,0.005061,0.1956,1
+0.8163,15.24,0.006773,0.01018,0.02662,0.004143,0.09915,1
+0.5066,14.0,0.00423,0.01169,0.01943,0.002177,0.1346,1
+1.77,77.11,0.007762,0.0996,0.04077,0.02286,0.222,1
+0.781,11.91,0.003796,0.01346,0.01536,0.001541,0.2028,1
+0.8652,17.12,0.005517,0.02045,0.01616,0.002922,0.1471,1
+1.065,16.64,0.003634,0.008268,0.01924,0.00152,0.0775,1
+1.321,109.9,0.005539,0.02664,0.01332,0.002256,0.3995,0
+1.35,22.73,0.007501,0.02714,0.0196,0.003913,0.1277,1
+0.8282,40.73,0.00609,0.02713,0.01594,0.002658,0.3508,0
+1.966,19.62,0.01289,0.003297,0.04243,0.001963,0.01335,1
+1.045,18.95,0.006175,0.01376,0.01096,0.001857,0.1514,1
+0.857,24.19,0.003818,0.02882,0.0191,0.002808,0.256,1
+0.9429,18.15,0.009282,0.02063,0.02183,0.002146,0.1444,1
+1.265,43.68,0.004877,0.02219,0.01535,0.002373,0.2992,0
+0.4607,10.5,0.00604,0.01514,0.01344,0.002206,0.2102,1
+1.031,11.68,0.005296,0.01723,0.0188,0.001941,0.1553,1
+1.077,43.95,0.004714,0.03697,0.01237,0.002556,0.6399,0
+1.476,525.6,0.01345,0.06389,0.04783,0.004476,0.3201,0
+0.8836,23.24,0.007337,0.005383,0.0194,0.00118,0.03469,1
+1.067,22.97,0.01038,0.09472,0.01219,0.01233,0.3021,1
+0.6457,17.37,0.006131,0.009075,0.01713,0.004414,0.09385,1
+0.9857,33.12,0.009197,0.08079,0.02773,0.006355,0.5897,0
+1.081,23.92,0.006692,0.005717,0.01416,0.002476,0.05307,1
+0.9195,19.41,0.004235,0.01457,0.01528,0.001593,0.1456,1
+1.398,67.78,0.008268,0.05042,0.02102,0.003854,0.5588,0
+0.8423,34.84,0.004123,0.01996,0.01055,0.003237,0.1856,1
+1.593,98.81,0.003899,0.02817,0.02674,0.005126,0.2623,0
+1.426,24.72,0.005427,0.04649,0.05628,0.004635,0.4504,0
+0.9227,24.79,0.007803,0.01835,0.01278,0.003856,0.1503,1
+1.153,36.35,0.004481,0.01358,0.01069,0.001435,0.135,1
+0.6336,119.3,0.009406,0.04344,0.03156,0.003362,0.2264,0
+0.8561,97.85,0.00491,0.02822,0.01956,0.00374,0.3948,0
+1.016,79.25,0.01082,0.035,0.0155,0.001948,0.2829,0
+1.363,20.74,0.005638,0.005254,0.01544,0.002087,0.05285,1
+2.22,38.87,0.009369,0.05371,0.02418,0.003249,0.3349,0
+2.2,31.16,0.007357,0.009959,0.03433,0.002961,0.02237,1
+1.373,25.22,0.005884,0.01872,0.01884,0.001817,0.1381,1
+1.805,19.08,0.01496,0.01453,0.03082,0.004785,0.03938,1
+1.743,25.78,0.009519,0.0199,0.02079,0.002701,0.1412,1
+0.7859,48.31,0.00624,0.02813,0.01397,0.002461,0.3791,0
+1.288,89.74,0.007997,0.03737,0.02897,0.003996,0.2544,0
+1.238,13.88,0.007595,0.01412,0.01792,0.001784,0.1316,1
+2.09,16.8,0.01291,0.004174,0.02572,0.002278,0.01005,1
+1.216,15.24,0.008732,0.01062,0.01824,0.003494,0.08434,1
+1.045,95.77,0.007974,0.04435,0.01617,0.005255,0.3533,0
+3.896,22.81,0.007594,0.0,0.01989,0.001773,0.0,1
+0.6342,71.0,0.004649,0.02749,0.01365,0.00255,0.4317,0
+1.911,24.2,0.009845,0.1027,0.03491,0.007877,0.4609,1
+0.9832,21.05,0.004452,0.02681,0.01454,0.003711,0.5539,0
+1.457,57.72,0.01056,0.05839,0.04022,0.006187,0.3344,0
+0.4875,11.64,0.004873,0.03318,0.01601,0.002289,0.3476,1
+0.469,12.68,0.004731,0.01652,0.01619,0.002081,0.1186,1
+1.687,11.28,0.006588,0.0145,0.01574,0.002268,0.0719,1
+1.409,16.39,0.0138,0.008347,0.01798,0.004261,0.04043,1
+1.304,20.67,0.009579,0.0,0.03004,0.002228,0.0,1
+0.6062,68.17,0.005015,0.03497,0.01543,0.003896,0.6091,0
+1.127,20.77,0.007364,0.05263,0.02161,0.00483,0.2939,1
+2.239,14.46,0.01205,0.04804,0.01843,0.004938,0.2,1
+1.014,32.65,0.0134,0.01162,0.02572,0.006164,0.08539,1
+1.033,52.34,0.005043,0.02117,0.01282,0.001892,0.3788,0
+1.545,170.0,0.006515,0.104,0.03112,0.005037,0.9608,0
+1.473,26.07,0.007802,0.01341,0.02086,0.002701,0.07698,1
+0.6594,25.18,0.006494,0.03137,0.01731,0.004392,0.1769,1
+1.563,10.08,0.008875,0.01808,0.01791,0.003317,0.08423,1
+1.376,18.15,0.008565,0.0643,0.01516,0.004976,0.4779,1
+0.4336,17.4,0.004133,0.01652,0.01371,0.002735,0.1759,1
+0.9168,72.44,0.006208,0.02375,0.01445,0.001906,0.2702,0
+1.182,6.802,0.005515,0.03735,0.01951,0.004583,0.1868,1
+1.075,48.55,0.005903,0.0473,0.01318,0.003892,0.3403,0
+2.904,16.97,0.0082,0.05738,0.01488,0.004738,0.363,1
+0.7655,17.86,0.006905,0.01978,0.01897,0.001671,0.1521,1
+1.15,40.09,0.003659,0.02572,0.01817,0.004108,0.3587,0
+1.073,54.18,0.007026,0.03188,0.01689,0.004142,0.4784,0
+0.6412,14.41,0.005231,0.03113,0.01639,0.005701,0.145,1
+1.621,20.2,0.006543,0.02991,0.01844,0.00269,0.1927,1
+1.492,29.84,0.007256,0.02071,0.0208,0.005304,0.1326,1
+1.006,19.98,0.003535,0.018,0.01254,0.001219,0.2437,1
+3.568,116.2,0.003139,0.0889,0.04484,0.01284,0.3639,0
+0.7213,25.7,0.006133,0.01615,0.02207,0.003563,0.1373,1
+0.6123,14.49,0.00335,0.01452,0.01113,0.00172,0.3728,0
+2.265,23.52,0.008738,0.04312,0.04192,0.005822,0.1397,1
+1.353,20.2,0.004455,0.02095,0.01641,0.001956,0.2282,1
+2.426,23.13,0.009861,0.04275,0.02475,0.002128,0.2923,1
+1.156,27.23,0.00911,0.05661,0.05963,0.009208,0.6869,0
+0.9567,8.205,0.008968,0.01588,0.02574,0.002582,0.0688,1
+0.9429,12.07,0.005954,0.05028,0.0175,0.004031,0.4341,1
+1.597,17.85,0.004973,0.01498,0.01724,0.001343,0.1062,1
+1.53,88.25,0.007548,0.03914,0.02168,0.004445,0.4634,0
+0.8121,48.29,0.007089,0.0236,0.02266,0.001463,0.1632,1
+0.5906,35.77,0.004117,0.02975,0.01295,0.002436,0.429,0
+1.24,45.4,0.005718,0.01998,0.0141,0.002085,0.2914,0
+0.6636,57.65,0.003872,0.0371,0.01964,0.003337,0.5755,0
+1.343,26.33,0.01127,0.02187,0.0158,0.003442,0.08669,1
+1.363,18.24,0.00744,0.02337,0.02203,0.004154,0.0935,1
+1.046,50.95,0.004369,0.01153,0.01302,0.001309,0.1048,1
+1.387,13.54,0.005158,0.01056,0.01718,0.002198,0.1067,1
+1.152,115.2,0.00874,0.02721,0.02045,0.004417,0.2639,0
+1.309,39.06,0.004426,0.03437,0.01675,0.004367,0.4024,0
+1.15,40.98,0.004626,0.01954,0.01547,0.00243,0.2902,0
+0.5664,20.65,0.005727,0.04393,0.02751,0.004572,0.3439,1
+1.193,102.5,0.006458,0.02945,0.01852,0.002608,0.3879,0
+1.486,24.6,0.01039,0.006416,0.02869,0.004821,0.01674,1
+3.647,35.13,0.007339,0.0,0.03141,0.003136,0.0,1
+2.261,27.48,0.01286,0.1197,0.0388,0.01792,0.3486,1
+0.9988,22.18,0.002826,0.01311,0.01013,0.001345,0.226,0
+1.599,23.94,0.007149,0.07743,0.01789,0.01008,1.105,0
+0.9173,28.09,0.004563,0.03872,0.01388,0.004081,0.5026,0
+1.657,20.62,0.00854,0.02945,0.01565,0.00384,0.2873,1
+1.56,83.16,0.009327,0.08958,0.02175,0.005195,0.7892,0
+0.5417,11.35,0.005212,0.02443,0.01818,0.004868,0.2569,1
+1.652,22.22,0.008146,0.01843,0.02015,0.001798,0.1603,1
+1.511,49.45,0.009976,0.05278,0.02653,0.005444,0.3219,1
+1.49,29.25,0.005298,0.1435,0.02566,0.01298,0.6783,1
+1.078,36.58,0.009769,0.05051,0.02981,0.003002,0.2322,0
+1.802,60.41,0.01061,0.03915,0.02186,0.003949,0.3458,0
+2.129,87.17,0.006455,0.04502,0.01829,0.003733,0.392,0
+1.51,21.57,0.007807,0.05112,0.0286,0.005715,0.2573,1
+0.8429,26.99,0.00638,0.01245,0.02292,0.001461,0.08105,1
+1.265,30.57,0.005421,0.04545,0.01869,0.004067,0.1901,1
+0.4966,19.88,0.004119,0.03644,0.01391,0.003204,0.3402,1
+1.051,224.1,0.005568,0.02096,0.01263,0.001803,0.2861,0
+1.441,34.62,0.007514,0.007665,0.04183,0.005953,0.02168,1
+1.216,75.09,0.006666,0.04062,0.01117,0.003727,0.5179,0
+1.408,67.74,0.005288,0.04256,0.01717,0.003211,0.5936,0
+0.4956,19.53,0.00329,0.01774,0.01172,0.002575,0.363,0
+1.161,133.0,0.006056,0.05638,0.01884,0.004787,0.6121,0
+1.961,32.52,0.009538,0.06019,0.02105,0.006,0.5911,0
+0.679,31.98,0.005532,0.03055,0.01177,0.002336,0.5018,0
+0.538,9.597,0.004474,0.02757,0.01212,0.004672,0.3365,1

pages/saved_models/logreg_breastcancer_reduced.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784071999edccf04023f52100df684df5df05ed87cbedf2fe265bb9dd779ce16
+size 1809

requirements.txt

@@ -0,0 +1,17 @@
+dash
+dash-bootstrap-components
+dash-core-components
+dash-html-components
+dash-table
+
+plotly
+
+pandas
+numpy
+
+scikit-learn
+joblib
+scipy
+threadpoolctl
+
+Pillow