main commit

Prediction.py

@@ -0,0 +1,130 @@
+import streamlit as st
+import pickle
+import json
+import pandas as pd
+# from sklearn.pipeline import make_pipeline
+# from sklearn.preprocessing import StandardScaler, OneHotEncoder
+# from sklearn.svm import SVC
+# from sklearn.linear_model import LogisticRegression
+# from sklearn.tree import DecisionTreeClassifier
+# from sklearn.ensemble import RandomForestClassifier
+
+
+with open('svc_model.pkl', 'rb') as f:
+    pipesvc = pickle.load(f)
+
+with open('logreg_model.pkl', 'rb') as f:
+    pipeLR = pickle.load(f)
+
+with open('dt_model.pkl', 'rb') as f:
+    pipeDT = pickle.load(f)
+
+with open('rf_model.pkl', 'rb') as f:
+    pipeRF = pickle.load(f)
+
+with open('preprocessor.pkl', 'rb') as f:
+    preprocessor = pickle.load(f)
+
+with open('le.pkl', 'rb') as f:
+    Le = pickle.load(f)
+
+with open('num_cols.json', 'r') as f:
+    numerical_cols = json.load(f)
+
+with open('cat_cols.json', 'r') as f:
+    categorical_cols = json.load(f)
+def run():
+    with st.form(key='form_prediksi'):
+        name = st.text_input('Nama', value='')
+        sex = st.radio('Kelamin', ('Perempuan', 'Laki-Laki'))
+        if sex=='Laki-Laki':
+            sexnum='M'
+        else: sexnum='F'
+        age= st.number_input('Umur', min_value=16, max_value=80, value=50, step=1)
+        smoking = st.radio('Apakah merokok?', ('Ya', 'Tidak'))
+        if smoking=='Ya':
+            smokingnum=2
+        else: smokingnum=1
+        Yelfing= st.radio('Apakah memiliki Yellow Finger?', ('Ya', 'Tidak'))
+        if Yelfing=='Ya':
+            yelfingnum=2
+        else: yelfingnum=1
+        anxeity = st.radio('Apakah memiliki Anxeity?', ('Ya', 'Tidak'))
+        if anxeity == 'Ya':
+            anxeitynum=2
+        else: anxeitynum=1
+        peer_pressure = st.radio('Apakah terdapat peer pressure?', ('Ya', 'Tidak'))
+        if peer_pressure=='Ya':
+            peer_pressurenum=2
+        else: peer_pressurenum=1
+        Crondis= st.radio('Apakah memiliki penyakit Kronis?', ('Ya', 'Tidak'))
+        if Crondis=='Ya':
+            crondisnum=2
+        else: crondisnum=1
+        Fatigue= st.radio('Apakah mudah capai?', ('Ya', 'Tidak'))
+        if Fatigue=='Ya':
+            fatiguenum=2
+        else: fatiguenum=1
+        alergi= st.radio('Apakah memiliki alergi?', ('Ya', 'Tidak'))
+        if alergi=='Ya':
+            alerginum=2
+        else: alerginum=1
+        mengi= st.radio('Apakah mengidap mengi?', ('Ya', 'Tidak'))
+        if mengi=='Ya':
+            menginum=2
+        else: menginum=1
+        Alkohol= st.radio('Apakah mengkonsumsi alkohol?', ('Ya', 'Tidak'))
+        if Alkohol=='Ya':
+            alkoholnum=2
+        else: alkoholnum=1
+        batuk= st.radio('Apakah ada batuk?', ('Ya', 'Tidak'))
+        if batuk=='Ya':
+            batuknum=2
+        else: batuknum=1
+        sesak= st.radio('Apakah terdapat sesak?', ('Ya', 'Tidak'))
+        if sesak=='Ya':
+            sesaknum=2
+        else: sesaknum=1
+        sutel= st.radio('Apakah susah untuk menalan?', ('Ya', 'Tidak'))
+        if sutel=='Ya':
+            sutelnum=2
+        else: sutelnum=1
+        sakda= st.radio('Apakah terdapat sakit di bagian dada?', ('Ya', 'Tidak'))
+        if sakda=='Ya':
+            sakdanum=2
+        else: sakdanum=1
+
+        submitted = st.form_submit_button('Predict')
+
+    data_inf = {'GENDER':sexnum,
+                'AGE': age, 
+                'SMOKING':smokingnum,
+                'YELLOW_FINGERS':yelfingnum, 
+                'ANXIETY':anxeitynum,
+                'PEER_PRESSURE':peer_pressurenum,
+                'CHRONIC DISEASE':crondisnum,
+                'FATIGUE ':fatiguenum, 
+                'ALLERGY ':alerginum,
+                'WHEEZING':menginum,
+                'ALCOHOL CONSUMING':alkoholnum,
+                'COUGHING':batuknum,
+                'SHORTNESS OF BREATH':sesaknum,
+                'SWALLOWING DIFFICULTY':sutelnum,
+                'CHEST PAIN':sakdanum
+    }
+
+
+
+    if submitted:
+        data_inf = pd.DataFrame([data_inf])
+        y_pred_inf_rf = pipeRF.predict(data_inf)
+        y_pred_inf_DT = pipeDT.predict(data_inf)
+        y_pred_inf_LR = pipeLR.predict(data_inf)
+        y_pred_inf_SVC = pipesvc.predict(data_inf)
+        st.write('# hasil inf dari Randomforest', Le.inverse_transform(y_pred_inf_rf))
+        st.write('# hasil inf dari Decision Tree', Le.inverse_transform(y_pred_inf_DT))
+        st.write('# hasil inf dari SVC', Le.inverse_transform(y_pred_inf_SVC))
+        st.write('# hasil inf dari Logistic regression', Le.inverse_transform(y_pred_inf_LR))
+
+if __name__== '__main__':
+    run()

app.py

@@ -0,0 +1,10 @@
+import streamlit as st
+import Prediction
+import eda
+
+navigation = st.sidebar.selectbox('Pilih Halaman: ', ('Predict', 'EDA'))
+
+if navigation == 'Predict':
+    Prediction.run()
+else:
+   eda.run()

cat_cols.json

@@ -0,0 +1 @@
+["GENDER"]

dt_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88766a40e0bdd36031d69dfeec60a997e2c1b904da5ab91bd2ae9d5519ee8657
+size 8212

eda.py

@@ -0,0 +1,101 @@
+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
+
+st.set_page_config(
+   page_title= 'Prediksi Diagnosis Kanker Paru-Paru',
+   layout='wide',
+   initial_sidebar_state='expanded'
+)
+
+def run():
+    image = Image.open('image.png')
+    resized_image = image.resize((300, 300))
+    st.image(resized_image, caption='Serangan jantung')
+
+    st.title('Prediksi Serangan Jantung')
+    df = pd.read_csv('https://raw.githubusercontent.com/Azrieldr/latihan/master/survey%20lung%20cancer.csv')
+    st.dataframe(df)
+
+
+    yes_percentage = (df['LUNG_CANCER'].value_counts(normalize=True)*100)['YES']
+    # Create pie chart
+    fig, ax = plt.subplots(figsize=(10,15), dpi=100)
+    ax.pie([yes_percentage, 100-yes_percentage], labels=['Positif', 'Negatif'], autopct='%1.1f%%')
+    ax.set_title('Persentase Diagnosis Kanker Paru-paru')
+    st.pyplot(fig)
+
+    persentaseByGender=df.groupby('GENDER')['LUNG_CANCER'].apply(lambda x: (x == 'YES').sum() / len(x) * 100)
+    print('persentase diagnosis kanker paru paru berdasarkan janis kelamin \n', persentaseByGender)
+    fig, ax = plt.subplots(figsize=(8, 6))
+    persentaseByGender.plot(kind='bar', ax=ax, color='#f4a7bb')
+    ax.set_title('Persentase Diagnosis Positif Berdasarkan Jenis Kelamin')
+    ax.set_xlabel('Jenis Kelamin')
+    ax.set_ylabel('Persentase (%)')
+    plt.xticks(rotation=0)
+    st.pyplot(fig)
+
+
+    # membuat dataframe copy dari dataframe awal
+    df1 = df.copy()
+
+    # membuat kolom baru dengan 1 berarti ya dan 0 berarti tidak
+    df1['Konsumsi Alkohol']=df1['ALCOHOL CONSUMING']-1
+    df1['Konsumsi Rokok']=df1['SMOKING']-1
+
+    #membuat table baru
+    persentaseByGender2=df1.groupby('GENDER')['Konsumsi Alkohol','Konsumsi Rokok'].mean()*100
+    persentaseByGender2=persentaseByGender2.T
+    fig, ax = plt.subplots(figsize=(8, 6))
+    persentaseByGender2.plot(kind='bar', ax=ax, color=['#f4a7bb','black'])
+    ax.set_title('Persentase Konsumsi Alkohol dan Rokok Berdasarkan Jenis Kelamin')
+    ax.set_xlabel('Jenis Kelamin')
+    ax.set_ylabel('Persentase (%)')
+    plt.xticks(rotation=0)
+    plt.legend(['F', 'M'])
+    st.pyplot(fig)
+
+    persentaseByAlc=df.groupby('ALCOHOL CONSUMING')['LUNG_CANCER'].apply(lambda x: (x == 'YES').sum() / len(x) * 100)
+    persentaseBySmk=df.groupby('SMOKING')['LUNG_CANCER'].apply(lambda x: (x == 'YES').sum() / len(x) * 100)
+
+    #merename sehingga nama kolom dari series baru yang akan dibuat berubah
+    persentaseByAlc=persentaseByAlc.rename('Alkohol')
+    persentaseBySmk=persentaseBySmk.rename('Rokok')
+
+    #sambungkan
+    gayaHidup=pd.concat([persentaseByAlc, persentaseBySmk], axis=1)
+    gayaHidup=gayaHidup.T
+
+    #membuat barplot
+    fig, ax = plt.subplots(figsize=(8, 6))
+    gayaHidup.plot(kind='bar', ax=ax, color=['#f4a7bb','black'])
+    ax.set_title('Persentase diagnosis berdasarkan gaya hidup')
+    ax.set_xlabel('Gaya Hidup')
+    ax.set_ylabel('Persentase (%)')
+    plt.xticks(rotation=0)
+    plt.legend(['Non-konsumen', 'Konsumen'])
+    st.pyplot(fig)
+
+    # membuat dataframe copy dari dataframe awal
+    df1 = df.copy()
+
+    # mengelompokkan data pada kolom AGE menjadi 5 kelompok
+    df1['group'] = pd.cut(df1['AGE'], bins=5)
+
+    # menghitung nilai rata-rata pada kolom LUNG_CANCER untuk setiap kelompok
+    result = df1.groupby('group')['LUNG_CANCER'].apply(lambda x: (x == 'YES').sum() / len(x) * 100)
+
+    # plot hasilnya menggunakan seaborn dengan barplot berwarna pink
+
+    sns.set_style('whitegrid')
+    fig, ax = plt.subplots(figsize=(8, 6))
+    ax = sns.barplot(x=result.index, y=result, color='pink')
+    ax.set(xlabel='AGE Group', ylabel='Percentage of LUNG_CANCER (YES)')
+    st.pyplot(fig)
+
+
+if __name__== '__main__':
+    run()

le.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98c239c5a3fa55f0f5b62419b22d2ec1447437e4152dd7fa3cad0d119e1b2fa
+size 253

logreg_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24cbd766152b5de614599341af5878f4973cf2ee305454d563b9dedda9c745da
+size 2963

num_cols.json

@@ -0,0 +1 @@
+["AGE", "SMOKING", "YELLOW_FINGERS", "ANXIETY", "PEER_PRESSURE", "CHRONIC DISEASE", "FATIGUE ", "ALLERGY ", "WHEEZING", "ALCOHOL CONSUMING", "COUGHING", "SHORTNESS OF BREATH", "SWALLOWING DIFFICULTY", "CHEST PAIN"]

preprocessor.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a626957a595c434e24a3d6b901c50091e2d6fe4b8e33858b0caca12b9087b18
+size 725

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+pandas
+seaborn
+matplotlib
+plotly
+numpy
+scikit-learn==1.0.2
+Pillow

rf_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e45e7da4c71b7dc406b3414ea0d210260c9ab75f07744c4f307abea5a685ac0
+size 551007