Upload 9 files

.gitattributes

@@ -29,3 +29,4 @@ 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
+star_classification.csv filter=lfs diff=lfs merge=lfs -text

Procfile

@@ -0,0 +1 @@
+web: sh setup.sh && streamlit run app.py

app.py

@@ -0,0 +1,73 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import pickle
+import base64
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+st.write("""
+# Stellar Detection App
+
+Stellar detection App adalah aplikasi untuk mendeteksi bintang star dan galaxy.
+ 
+Aplikasi ini mendeteksi bintang menggunakan data Stellar Classification.
+
+""")
+
+url_dataset = f'<a href="churn_data.csv">Download Dataset CSV File</a>'
+st.markdown(url_dataset, unsafe_allow_html=True)
+
+def user_input_features() :
+    alpha = st.sidebar.slider('Alpha', 0.005528,359.99981)
+    delta = st.sidebar.slider('Delta', -18.785328,83.000519)
+    u = st.sidebar.slider('U', -9999.0,32.78139)
+    g = st.sidebar.slider('G', -9999.0,31.60224)
+    r = st.sidebar.slider('R', 9.82207,29.57186)
+    i = st.sidebar.slider('I', 9.469903,32.14147)
+    z = st.sidebar.slider('Z', -9999.0,29.38374)
+    redshift = st.sidebar.slider('Redshift', -0.009971,7.011245)
+
+    data = {'alpha':[alpha], 
+            'delta':[delta],
+            'u':[u],
+            'g':[g],
+            'r':[r],
+            'i':[i],
+            'z':[z],
+            'redshift':[redshift]}
+
+    features = pd.DataFrame(data)
+    return features
+
+input_df = user_input_features()
+
+
+star_raw = pd.read_csv('star_classification.csv')
+star_raw.fillna(0, inplace=True)
+star = star_raw.drop(columns=['class'])
+df = pd.concat([input_df,star],axis=0)
+
+
+df = df[:1] # Selects only the first row (the user input data)
+df.fillna(0, inplace=True)
+
+features = ['alpha', 'delta', 'u', 'g', 'r', 'i', 'z', 'redshift']
+
+df = df[features]
+
+
+st.subheader('User Input features')
+st.write(df)
+
+load_clf = pickle.load(open('stellar_clf.pkl', 'rb'))
+detect = load_clf.predict(df)
+detect_proba = load_clf.predict_proba(df)
+star_labels = np.array(['Not Star','Star'])
+st.subheader('Detection')
+st.write(star_labels[detect[0]])
+st.subheader('Detection Probability')
+df_prob = pd.DataFrame(data = detect_proba,
+                    index = ['Probability'],
+                    columns = star_labels)
+st.write(df_prob)

requirements.txt

@@ -0,0 +1,6 @@
+matplotlib==3.5.1
+numpy==1.21.5
+pandas==1.4.2
+seaborn==0.11.2
+streamlit==1.13.0
+sklearn

setup.sh

@@ -0,0 +1,13 @@
+mkdir -p ~/.streamlit/
+
+echo "\
+[general]\n\
+email = \"your-email@domain.com\"\n\
+" > ~/.streamlit/credentials.toml
+
+echo "\
+[server]\n\
+headless = true\n\
+enableCORS=false\n\
+port = $PORT\n\
+" > ~/.streamlit/config.toml

star_classification.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faefcad9b950309282024dd351289ee14ae30f65a7b2ef32c9fa442da9dbe585
+size 16755863

stellar_clf.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfd151d9ca61bb1ce0f76a575962b5b141f7d9721749699214da4b23ae2e03d
+size 6761510

stellar_model.ipynb

@@ -0,0 +1,245 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c2f352ed",
+   "metadata": {},
+   "source": [
+    "# Dataset\n",
+    "\n",
+    "https://www.kaggle.com/datasets/fedesoriano/stellar-classification-dataset-sdss17?resource=download"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "dff0477d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd \n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "import pickle"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "53a8cd69",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "         obj_ID       alpha      delta         u         g         r  \\\n",
+      "0  1.237661e+18  135.689107  32.494632  23.87882  22.27530  20.39501   \n",
+      "1  1.237665e+18  144.826101  31.274185  24.77759  22.83188  22.58444   \n",
+      "2  1.237661e+18  142.188790  35.582444  25.26307  22.66389  20.60976   \n",
+      "3  1.237663e+18  338.741038  -0.402828  22.13682  23.77656  21.61162   \n",
+      "4  1.237680e+18  345.282593  21.183866  19.43718  17.58028  16.49747   \n",
+      "\n",
+      "          i         z  run_ID  rerun_ID  cam_col  field_ID   spec_obj_ID  \\\n",
+      "0  19.16573  18.79371    3606       301        2        79  6.543777e+18   \n",
+      "1  21.16812  21.61427    4518       301        5       119  1.176014e+19   \n",
+      "2  19.34857  18.94827    3606       301        2       120  5.152200e+18   \n",
+      "3  20.50454  19.25010    4192       301        3       214  1.030107e+19   \n",
+      "4  15.97711  15.54461    8102       301        3       137  6.891865e+18   \n",
+      "\n",
+      "    class  redshift  plate    MJD  fiber_ID  \n",
+      "0  GALAXY  0.634794   5812  56354       171  \n",
+      "1  GALAXY  0.779136  10445  58158       427  \n",
+      "2  GALAXY  0.644195   4576  55592       299  \n",
+      "3  GALAXY  0.932346   9149  58039       775  \n",
+      "4  GALAXY  0.116123   6121  56187       842  \n"
+     ]
+    }
+   ],
+   "source": [
+    "pd.set_option('display.max_columns', None)\n",
+    "pd.set_option('display.max_rows', None)\n",
+    "df_star = pd.read_csv('star_classification.csv')\n",
+    "print(df_star.head())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "55f05a40",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['obj_ID', 'alpha', 'delta', 'u', 'g', 'r', 'i', 'z', 'run_ID',\n",
+       "       'rerun_ID', 'cam_col', 'field_ID', 'spec_obj_ID', 'class', 'redshift',\n",
+       "       'plate', 'MJD', 'fiber_ID'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_star.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "e468f78d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "obj_ID         1237645942904389888.0\n",
+       "alpha                       0.005528\n",
+       "delta                     -18.785328\n",
+       "u                            -9999.0\n",
+       "g                            -9999.0\n",
+       "r                            9.82207\n",
+       "i                           9.469903\n",
+       "z                            -9999.0\n",
+       "run_ID                           109\n",
+       "rerun_ID                         301\n",
+       "cam_col                            1\n",
+       "field_ID                          11\n",
+       "spec_obj_ID     299519089380976640.0\n",
+       "class                         GALAXY\n",
+       "redshift                   -0.009971\n",
+       "plate                            266\n",
+       "MJD                            51608\n",
+       "fiber_ID                           1\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_star.min()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "e1b7eff1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "obj_ID          1237680531356386304.0\n",
+       "alpha                       359.99981\n",
+       "delta                       83.000519\n",
+       "u                            32.78139\n",
+       "g                            31.60224\n",
+       "r                            29.57186\n",
+       "i                            32.14147\n",
+       "z                            29.38374\n",
+       "run_ID                           8162\n",
+       "rerun_ID                          301\n",
+       "cam_col                             6\n",
+       "field_ID                          989\n",
+       "spec_obj_ID    14126940609093851136.0\n",
+       "class                            STAR\n",
+       "redshift                     7.011245\n",
+       "plate                           12547\n",
+       "MJD                             58932\n",
+       "fiber_ID                         1000\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_star.max()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "aba35ef0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = df_star.drop('class', axis=1)\n",
+    "Y = df_star['class']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ec2e27b9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "RandomForestClassifier()"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clf = RandomForestClassifier()\n",
+    "clf.fit(X, Y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "0fb83c09",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pickle.dump(clf, open('stellar_clf.pkl', 'wb'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a6fab8b2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.12"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "a07fda4108288eac30d110fb6c0835906d2e1f106803cd94f31ab0c859b7a7bd"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}