Skip to content

Ml with dashboard #12

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
lenasph merged 2 commits into from
Jul 11, 2025
Merged

Ml with dashboard #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
34d7357
testing unseen data
Jul 11, 2025
10468d8
Update dashboard.py
lenasph Jul 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
171 changes: 114 additions & 57 deletions dashboard.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -674,8 +674,8 @@ def create_weight_boxplot():
]),
style={
'width': '100%',
'height': '80px',
'lineHeight': '80px',
'height': '100px',
'lineHeight': '60px',
'borderWidth': '2px',
'borderStyle': 'dashed',
'borderColor': '#4c96df',
Expand All @@ -684,6 +684,10 @@ def create_weight_boxplot():
'backgroundColor': '#f8f9fa',
'cursor': 'pointer',
'marginBottom': '20px',
'display': 'flex',
'alignItems': 'center',
'justifyContent': 'center',
'padding': '10px',
},
multiple=False
),
Expand All @@ -701,8 +705,9 @@ def create_weight_boxplot():
html.Div(
[
html.H4(
"📊 Einschätzung",
"Einschätzung",
style={
"fontSize": "20px",
"fontWeight": "bold",
"marginBottom": "20px",
"color": "#4c96df",
Expand All @@ -724,8 +729,10 @@ def create_weight_boxplot():
style={
"minHeight": "100px",
"display": "flex",
"alignItems": "center",
"justifyContent": "center",
"flexDirection": "column",
"alignItems": "stretch",
"justifyContent": "flex-start",
"gap": "0",
}
)
],
Expand Down Expand Up @@ -868,62 +875,15 @@ def update_prediction(contents, filename):

# Datei-Informationen anzeigen
file_info = [
# Erste Kachel: Raucher-Wahrscheinlichkeit
html.Div([
html.H5(
f"📄 Datei erfolgreich geladen: {filename}",
style={
"color": "#27ae60",
"fontWeight": "bold",
"marginBottom": "15px",
"textAlign": "center"
}
),
html.Div([
html.P(f"Anzahl Zeilen: {len(df_uploaded)}", style={"margin": "5px 0", "fontWeight": "bold"}),
html.P(f"Anzahl Spalten: {len(df_uploaded.columns)}", style={"margin": "5px 0", "fontWeight": "bold"}),
html.P(f"Spalten: {', '.join(df_uploaded.columns)}", style={"margin": "5px 0", "fontSize": "14px"}),
], style={
"backgroundColor": "#f8f9fa",
"padding": "15px",
"borderRadius": "8px",
"marginBottom": "20px",
"border": "1px solid #e9ecef"
})
]),

# Vorschau der ersten Zeilen
html.Div([
html.H6("📊 Datenvorschau (erste 5 Zeilen):", style={"fontWeight": "bold", "marginBottom": "10px"}),
html.Div([
html.Table([
html.Thead([
html.Tr([html.Th(col, style={"padding": "8px", "backgroundColor": "#f1f8ff", "fontWeight": "bold"}) for col in df_uploaded.columns])
]),
html.Tbody([
html.Tr([
html.Td(str(df_uploaded.iloc[i][col]), style={"padding": "8px", "borderBottom": "1px solid #dee2e6"})
for col in df_uploaded.columns
]) for i in range(min(5, len(df_uploaded)))
])
], style={
"width": "100%",
"borderCollapse": "collapse",
"border": "1px solid #dee2e6",
"fontSize": "14px"
})
], style={"overflowX": "auto", "marginBottom": "20px"})
]),

# Vorhersage-Ergebnis
html.Div([
html.Hr(style={"margin": "20px 0", "border": "1px solid #e9ecef"}),
html.P(
f"🎯 Raucher-Wahrscheinlichkeit:",
f"🚬 Raucher-Wahrscheinlichkeit 🚬",
style={
"textAlign": "center",
"fontWeight": "bold",
"marginBottom": "10px",
"color": "#2c3e50",
"color": "#4c96df",
"fontSize": "18px",
}
),
Expand All @@ -948,7 +908,73 @@ def update_prediction(contents, filename):
"marginTop": "10px",
}
)
])
], style={
"backgroundColor": "#ffffff",
"padding": "30px",
"borderRadius": "8px",
"marginBottom": "10px",
"border": "1px solid #e9ecef",
"boxShadow": "0 2px 8px rgba(0,0,0,0.1)",
"flex": "1",
"minHeight": "200px",
"display": "flex",
"flexDirection": "column",
"justifyContent": "center",
}),

# Zweite Kachel: Datenvorschau mit Datei-Informationen
html.Div([
html.H5(
f"Datenvorschau: {filename}",
style={
"color": "#4c96df",
"fontSize": "18px",
"fontWeight": "bold",
"marginBottom": "15px",
"textAlign": "center"
}
),
html.Div([
html.P(f"Anzahl Zeilen: {len(df_uploaded)} | Anzahl Spalten: {len(df_uploaded.columns)}",
style={"margin": "10px 0", "fontWeight": "bold", "textAlign": "center"}),
], style={
"backgroundColor": "#f8f9fa",
"padding": "10px",
"borderRadius": "8px",
"border": "1px solid #e9ecef",
"marginBottom": "15px"
}),
html.Div([
html.Table([
html.Thead([
html.Tr([html.Th(col, style={"padding": "8px", "backgroundColor": "#f1f8ff", "fontWeight": "bold"}) for col in df_uploaded.columns[:10]])
]),
html.Tbody([
html.Tr([
html.Td(str(df_uploaded.iloc[i][col]), style={"padding": "8px", "borderBottom": "1px solid #dee2e6"})
for col in df_uploaded.columns[:10]
]) for i in range(min(5, len(df_uploaded)))
])
], style={
"width": "100%",
"borderCollapse": "collapse",
"border": "1px solid #dee2e6",
"fontSize": "14px"
})
], style={"overflowX": "auto"})
], style={
"backgroundColor": "#ffffff",
"padding": "20px",
"borderRadius": "8px",
"marginBottom": "0px",
"border": "1px solid #e9ecef",
"boxShadow": "0 2px 8px rgba(0,0,0,0.1)",
"flex": "1",
"minHeight": "200px",
"display": "flex",
"flexDirection": "column",
"justifyContent": "flex-start",
})
]

return file_info
Expand Down Expand Up @@ -990,6 +1016,37 @@ def update_prediction(contents, filename):
])
]

# Zusätzlicher Callback für Upload-Status
@app.callback(
Output('upload-csv', 'children'),
Input('upload-csv', 'contents'),
State('upload-csv', 'filename')
)
def update_upload_status(contents, filename):
if contents is None:
return html.Div([
html.P("CSV-Datei hier hineinziehen oder klicken zum Auswählen"),
], style={"textAlign": "center", "margin": "0"})
else:
return html.Div([
html.Div([
html.Span("✅", style={"fontSize": "24px", "marginRight": "10px", "color": "#27ae60"}),
html.Span(f"Datei hochgeladen: {filename}", style={"fontWeight": "bold", "color": "#27ae60"}),
], style={
"display": "flex",
"alignItems": "center",
"justifyContent": "center",
"marginBottom": "8px"
}),
html.P("Klicken Sie hier, um eine neue Datei hochzuladen",
style={
"fontSize": "12px",
"color": "#7f8c8d",
"margin": "0",
"textAlign": "center"
})
], style={"display": "flex", "flexDirection": "column", "justifyContent": "center", "height": "100%"})

# Dash-Anwendung ausführen -----------------------------------------------------------------------------------------------------------
if __name__ == "__main__":
app.run(debug=True) # Debug Modus für Ausgabe von Fehlermeldungen im Dashboard uvm
app.run(debug=True) # Debug Modus für Ausgabe von Fehlermeldungen im Dashboard uvm
61 changes: 61 additions & 0 deletions smoker-models.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1495,6 +1495,67 @@
"plt.show()"
]
},
{
"cell_type": "markdown",
"id": "8614c6c0",
"metadata": {},
"source": [
"## Testing Model on unseen Data"
]
},
{
"cell_type": "code",
"execution_count": 161,
"id": "cf8fc705",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Random Forest Test Accuracy: 0.7478\n",
"Random Forest Train Accuracy: 1.0000\n",
"Random Forest Test F1-Score: 0.6501\n",
"Random Forest Train F1-Score: 1.0000\n",
"Random Forest Test Mean Squared Error: 0.2522\n",
"Random Forest Train Mean Squared Error: 0.0000\n"
]
}
],
"source": [
"# Daten vorbereiten\n",
"X = df_train.drop('smoking', axis=1)\n",
"X_test = df_test_unseen.drop('smoking', axis=1)\n",
"y = df_train['smoking']\n",
"y_test = df_test_unseen['smoking']\n",
"\n",
"# Random Forest Modell trainieren\n",
"rfc = RandomForestClassifier(random_state=0, n_estimators=700, max_depth=40, max_features='sqrt', min_samples_leaf=1)\n",
"rfc.fit(X, y)\n",
"\n",
"# Vorhersagen berechnen\n",
"y_pred_train = rfc.predict(X)\n",
"y_pred = rfc.predict(X_test)\n",
"\n",
"# Metriken berechnen\n",
"accuracy_train = accuracy_score(y, y_pred_train)\n",
"accuracy_test = accuracy_score(y_test, y_pred)\n",
"\n",
"f1_train = f1_score(y, y_pred_train)\n",
"f1_test = f1_score(y_test, y_pred)\n",
"\n",
"mse_train = mean_squared_error(y, y_pred_train)\n",
"mse_test = mean_squared_error(y_test, y_pred)\n",
"\n",
"# Ergebnisse ausgeben\n",
"print(f\"Random Forest Test Accuracy: {accuracy_test:.4f}\")\n",
"print(f\"Random Forest Train Accuracy: {accuracy_train:.4f}\")\n",
"print(f\"Random Forest Test F1-Score: {f1_test:.4f}\")\n",
"print(f\"Random Forest Train F1-Score: {f1_train:.4f}\")\n",
"print(f\"Random Forest Test Mean Squared Error: {mse_test:.4f}\")\n",
"print(f\"Random Forest Train Mean Squared Error: {mse_train:.4f}\")\n"
]
},
{
"cell_type": "markdown",
"id": "09fc7c9b",
Expand Down
Loading