Upload 12 files

Model_Deployment_Inference.ipynb

@@ -0,0 +1,357 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "NnI3VscLsD6z"
+      },
+      "outputs": [],
+      "source": [
+        "#import library\n",
+        "\n",
+        "import pickle\n",
+        "import json\n",
+        "import pandas as pd\n",
+        "import numpy as np"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "ZuS5HPBkBbZ4",
+        "outputId": "7561ff89-4d83-48c3-b809-28e633e72508"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Name: scikit-learn\n",
+            "Version: 1.5.1\n",
+            "Summary: A set of python modules for machine learning and data mining\n",
+            "Home-page: https://scikit-learn.org\n",
+            "Author: \n",
+            "Author-email: \n",
+            "License: new BSD\n",
+            "Location: /opt/anaconda3/envs/phase1/lib/python3.12/site-packages\n",
+            "Requires: joblib, numpy, scipy, threadpoolctl\n",
+            "Required-by: feature-engine\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip show scikit-learn"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bDmKBK0SolkE"
+      },
+      "source": [
+        "### load model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {
+        "id": "4aqmhcqinrlU"
+      },
+      "outputs": [],
+      "source": [
+        "#Load model\n",
+        "\n",
+        "with open('list_cat_cols.txt', 'r') as file_1:\n",
+        "  list_cat_col = json.load(file_1)\n",
+        "\n",
+        "with open('list_num_cols.txt', 'r') as file_2:\n",
+        "  list_num_col = json.load(file_2)\n",
+        "\n",
+        "with open('model_encoder.pkl', 'rb') as file_3:\n",
+        "  model_encoder = pickle.load(file_3)\n",
+        "\n",
+        "with open('model_scaler.pkl', 'rb') as file_4:\n",
+        "  model_scaler = pickle.load(file_4)\n",
+        "\n",
+        "with open('model_lin_reg.pkl', 'rb') as file_5:\n",
+        "  model_lin_reg = pickle.load(file_5)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Ra7wa9DyokUs"
+      },
+      "source": [
+        "###Inferece"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 100
+        },
+        "id": "_6zz1wBVoYFG",
+        "outputId": "e7389c1d-6944-45e7-a7d2-311fdc3b022d"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>Name</th>\n",
+              "      <th>Age</th>\n",
+              "      <th>Height</th>\n",
+              "      <th>Weight</th>\n",
+              "      <th>Price</th>\n",
+              "      <th>AttackingWorkRate</th>\n",
+              "      <th>DefensiveWorkRate</th>\n",
+              "      <th>PaceTotal</th>\n",
+              "      <th>ShootingTotal</th>\n",
+              "      <th>PassingTotal</th>\n",
+              "      <th>DribblingTotal</th>\n",
+              "      <th>DefendingTotal</th>\n",
+              "      <th>PhysicalityTotal</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>Hana</td>\n",
+              "      <td>50</td>\n",
+              "      <td>180</td>\n",
+              "      <td>70</td>\n",
+              "      <td>30000000</td>\n",
+              "      <td>Medium</td>\n",
+              "      <td>Low</td>\n",
+              "      <td>60</td>\n",
+              "      <td>80</td>\n",
+              "      <td>30</td>\n",
+              "      <td>70</td>\n",
+              "      <td>60</td>\n",
+              "      <td>80</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "   Name  Age  Height  Weight     Price AttackingWorkRate DefensiveWorkRate  \\\n",
+              "0  Hana   50     180      70  30000000            Medium               Low   \n",
+              "\n",
+              "   PaceTotal  ShootingTotal  PassingTotal  DribblingTotal  DefendingTotal  \\\n",
+              "0         60             80            30              70              60   \n",
+              "\n",
+              "   PhysicalityTotal  \n",
+              "0                80  "
+            ]
+          },
+          "execution_count": 4,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        " #Create new data\n",
+        "#Gunakan keseluruhan data\n",
+        "\n",
+        "data_inf = {\n",
+        "    'Name' : 'Hana',\n",
+        "    'Age' : 50,\n",
+        "    'Height' : 180,\n",
+        "    'Weight' : 70,\n",
+        "    'Price' : 30000000,\n",
+        "    'AttackingWorkRate' : 'Medium',\n",
+        "    'DefensiveWorkRate' : 'Low',\n",
+        "    'PaceTotal' :60,\n",
+        "    'ShootingTotal': 80,\n",
+        "    'PassingTotal' : 30,\n",
+        "    'DribblingTotal' :70,\n",
+        "    'DefendingTotal' :60,\n",
+        "    'PhysicalityTotal':80,\n",
+        "}\n",
+        "\n",
+        "data_inf = pd.DataFrame([data_inf])\n",
+        "data_inf"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 80
+        },
+        "id": "JHPUX35kpjyL",
+        "outputId": "a30b72c5-036a-46fe-e0dd-1a61788d0dc5"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>Age</th>\n",
+              "      <th>Height</th>\n",
+              "      <th>Weight</th>\n",
+              "      <th>Price</th>\n",
+              "      <th>PaceTotal</th>\n",
+              "      <th>ShootingTotal</th>\n",
+              "      <th>PassingTotal</th>\n",
+              "      <th>DribblingTotal</th>\n",
+              "      <th>DefendingTotal</th>\n",
+              "      <th>PhysicalityTotal</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>50</td>\n",
+              "      <td>180</td>\n",
+              "      <td>70</td>\n",
+              "      <td>30000000</td>\n",
+              "      <td>60</td>\n",
+              "      <td>80</td>\n",
+              "      <td>30</td>\n",
+              "      <td>70</td>\n",
+              "      <td>60</td>\n",
+              "      <td>80</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "   Age  Height  Weight     Price  PaceTotal  ShootingTotal  PassingTotal  \\\n",
+              "0   50     180      70  30000000         60             80            30   \n",
+              "\n",
+              "   DribblingTotal  DefendingTotal  PhysicalityTotal  \n",
+              "0              70              60                80  "
+            ]
+          },
+          "execution_count": 5,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "#split between numerical and categorical columns\n",
+        "\n",
+        "data_inf_num = data_inf[list_num_col]\n",
+        "data_inf_cat = data_inf[list_cat_col]\n",
+        "data_inf_num"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "metadata": {
+        "id": "Yligyt0up4Ld"
+      },
+      "outputs": [],
+      "source": [
+        "#feature scaling and encoding\n",
+        "\n",
+        "data_inf_num_scaled = model_scaler.transform(data_inf_num)\n",
+        "data_inf_cat_encoded = model_encoder.transform(data_inf_cat)\n",
+        "data_inf_final = np.concatenate([data_inf_num_scaled, data_inf_cat_encoded], axis = 1)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "5EBS6wQYqUfb",
+        "outputId": "a29e15a7-27dd-4284-8152-9ba9a69a1916"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "array([82.7433109])"
+            ]
+          },
+          "execution_count": 7,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "#predict using linear reg model\n",
+        "\n",
+        "y_pred_inf = model_lin_reg.predict(data_inf_final)\n",
+        "y_pred_inf"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "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": "3.12.4"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

app.py

@@ -0,0 +1,10 @@
+import streamlit as st
+import eda
+import prediction
+
+page = st.sidebar.selectbox('Choose page: ', ('EDA', 'Prediction'))
+
+if page == 'EDA':
+    eda.run()
+else:
+    prediction.run()

eda.py

@@ -0,0 +1,65 @@
+import streamlit as st
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+import plotly.express as px
+from PIL import Image
+
+def run():
+
+    # Create title
+    st.title('FIFA 2022 Player Rating Prediction')
+
+    # Create subheader
+    st.subheader('EDA untuk Analys FIFA Rating 2022')
+
+    # Insert image 
+    image = Image.open('bola.jpeg')
+    st.image(image, caption = 'FIFA 2022')
+
+    # Create text
+    st.write('This page is written by Brenda')
+
+    # Bold
+    st.write('**Tes**')
+
+    # Italic
+    st.write('*Tes*')
+
+    # Make font size
+    st.write('# Halo')
+    st.write('## Halo')
+
+    # Make a straight line
+    st.markdown('---')
+
+    # Load and show datafrane
+    df = pd.read_csv('https://raw.githubusercontent.com/ardhiraka/FSDS_Guidelines/master/p1/v3/w1/P1W1D1PM%20-%20Machine%20Learning%20Problem%20Framing.csv')
+    st.dataframe(df)
+
+    # Make a barplot
+    st.write('#### Plot AttackingWorkRate')
+    fig = plt.figure(figsize=(15,5))
+    sns.countplot(x = 'AttackingWorkRate', data = df)
+    st.pyplot(fig)
+
+    # Make a histogram
+    st.write('#### Histogram of Rating')
+    fig = plt.figure(figsize = (15,5))
+    sns.histplot(df['Overall'], bins = 30, kde = True)
+    st.pyplot(fig)
+
+    # Make a histogram based on user input
+    st.write('#### Histogram based on user input')
+    option = st.selectbox('Choose a column', ('Age', 'Weight', 'ShootingTotal'))
+    fig = plt.figure(figsize = (15,5))
+    sns.histplot(df[option], bins = 30, kde = True)
+    st.pyplot(fig)
+
+    # Make visualisation with plotly plot
+    st.write('#### Plotly plot - ValueEUR Vs Overall (Rating)')
+    fig = px.scatter(df, x = 'ValueEUR', y = 'Overall', hover_data = ['Name', 'Age'])
+    st.plotly_chart(fig)
+
+if __name__ == '__main__':
+    run()

list_cat_cols.txt

@@ -0,0 +1 @@
+["AttackingWorkRate", "DefensiveWorkRate"]

list_num_cols.txt

@@ -0,0 +1 @@
+["Age", "Height", "Weight", "Price", "PaceTotal", "ShootingTotal", "PassingTotal", "DribblingTotal", "DefendingTotal", "PhysicalityTotal"]

model_encoder.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0b8c0b58197ff3f7593e599ac7d22ed2e7872305c34b0285e90cb9af9a0422
+size 636

model_lin_reg.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38351e88399327d968436b0310e0606bdb1c4dbd479204fd1bc83388eb3c20e2
+size 595

model_scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:113fcf87816e12fe474fc1568f74fa2d57f4c4f54588a6ee065329b4cfcaad16
+size 1096

prediction.py

@@ -0,0 +1,87 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import pickle
+import json
+
+# Load all files
+
+with open('list_cat_cols.txt', 'r') as file_1:
+  list_cat_col = json.load(file_1)
+
+with open('list_num_cols.txt', 'r') as file_2:
+  list_num_col = json.load(file_2)
+
+with open('model_encoder.pkl', 'rb') as file_3:
+  model_encoder = pickle.load(file_3)
+
+with open('model_scaler.pkl', 'rb') as file_4:
+  model_scaler = pickle.load(file_4)
+
+with open('model_lin_reg.pkl', 'rb') as file_5:
+  model_lin_reg = pickle.load(file_5)
+
+def run():
+  
+  # Make form to fill data
+    with st.form('form_fifa_2022'):
+        # Use text_input
+        name = st.text_input('Name: ', value = '')
+        # Use number_input
+        age = st.number_input('Age: ', value = 25, min_value = 15, max_value = 60, help = 'Fill with player age')
+        height = st.number_input('Height', value = 170, min_value = 150, max_value = 250)
+        # Use a slider
+        weight = st.slider('Weight: ', min_value = 50, max_value = 100, value = 70)
+        # Price
+        price  = st.number_input('Price: ', value = 0, min_value = 0)
+        st.markdown('---')
+
+        attacking_work_rate = st.selectbox('Attacking Work Rate: ', ('Low', 'Medium', 'High'), index= 1)
+        defensive_work_rate = st.selectbox('Defensive Work Rate: ', ('Low', 'Medium', 'High'), index= 1)
+
+        pace = st.number_input('Pace: ', min_value =0, max_value = 100, value = 10)
+        shooting = st.number_input('Shooting: ', min_value =0, max_value = 100, value = 10)
+        passing = st.number_input('Passing: ', min_value =0, max_value = 100, value = 10)
+        dribbling = st.number_input('Dribbling: ', min_value =0, max_value = 100, value = 10)
+        defending = st.number_input('Defending: ', min_value =0, max_value = 100, value = 10)
+        physicality = st.number_input('Physicality: ', min_value =0, max_value = 100, value = 10)
+
+        # Define submit button form
+        submitted = st.form_submit_button('Predict')
+
+    data_inf = {
+        'Name' : name,
+        'Age' : age,
+        'Height' : height,
+        'Weight' : weight,
+        'Price' : price,
+        'AttackingWorkRate' : attacking_work_rate,
+        'DefensiveWorkRate' :defensive_work_rate,
+        'PaceTotal' : pace,
+        'ShootingTotal': shooting,
+        'PassingTotal' : passing,
+        'DribblingTotal' : dribbling,
+        'DefendingTotal' : defending,
+        'PhysicalityTotal': physicality,
+    }
+
+    data_inf = pd.DataFrame([data_inf])
+    st.dataframe(data_inf)
+
+    if submitted:
+        # Split
+        data_inf_num = data_inf[list_num_col]
+        data_inf_cat = data_inf[list_cat_col]
+
+        # Scaling, Encoding, Concatenate
+        data_inf_num_scaled = model_scaler.transform(data_inf_num)
+        data_inf_cat_encoded = model_encoder.transform(data_inf_cat)
+        data_inf_final = np.concatenate([data_inf_num_scaled, data_inf_cat_encoded], axis = 1)
+
+        # Predict
+        y_pred_inf = model_lin_reg.predict(data_inf_final)
+
+        st.write('## Rating: ', str(int(y_pred_inf)))
+
+if __name__ == '__main__':
+    run()

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+pandas
+seaborn
+matplotlib
+numpy
+scikit-learn == 1.3.2
+Pillow
+plotly