Spaces:
Sleeping
Sleeping
File size: 21,109 Bytes
6a19a00 e1c2643 6a19a00 818b3fc 6a19a00 627911a 6a19a00 627911a 6a19a00 818b3fc 6a19a00 1acc247 6a19a00 1acc247 6a19a00 57c18a7 6a19a00 fc8ccc7 b6bdba6 fc8ccc7 6a19a00 57c18a7 b6bdba6 6a19a00 fc8ccc7 b6bdba6 fc8ccc7 6a19a00 fc8ccc7 6a19a00 e1c2643 6939570 6a19a00 57c18a7 b6bdba6 fc8ccc7 b6bdba6 fc8ccc7 6a19a00 e1c2643 40a3917 6a19a00 57c18a7 b6bdba6 fc8ccc7 b6bdba6 fc8ccc7 6a19a00 fc0db7a c4e746f 6a19a00 a09a604 6a19a00 a09a604 40a3917 028535f 6a19a00 fc0db7a c4e746f fc0db7a 6a19a00 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 |
import streamlit as st, base64
import pandas as pd, seaborn as sns
import os, matplotlib.pyplot as plt
import pickle, numpy as np, xgboost as xgb
from keras.models import load_model
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import classification_report, accuracy_score, confusion_matrix
# image de fond
def add_bg_from_local(image_file):
with open(image_file, "rb") as image_file:
encoded_string = base64.b64encode(image_file.read())
st.markdown(
f"""
<style>
.stApp {{
background-image: url(data:image/{"png"};base64,{encoded_string.decode()});
background-size: cover
}}
</style>
""",
unsafe_allow_html=True
)
add_bg_from_local('route.png')
fig = plt.figure(figsize=(10, 10))
_, middle, _ = st.columns((2, 3, 2))
with middle:
st.title(":orange[_Scoring App_]")
# path du dossier data
#path = ".\data"
# fonction pour loader le dataset
@st.cache_data
def load_data(file_path):
return pd.read_csv(file_path)
# convertir dataframe en csv
def convert_df_to_csv(frame):
return frame.to_csv(index=False).encode("utf-8")
# fonction principale
st.sidebar.image("picture1.png")
def main():
st.markdown("<h2 style = 'text-align:center; \
color:green;'> Classification pour l'octroi de credit </h2>", unsafe_allow_html = True)
# charger le fichier
uploaded_file = st.sidebar.file_uploader("Importer fichier csv", type=["csv"])
# creation du menu
menu = ["Home", "Data Exploration", "Data Visualisation", "Make prediction"]
choice = st.sidebar.selectbox("Select menu", menu)
# charger le jeu de donnees
data = load_data("loan.csv")
# supprime la colonne Loan_ID
data.drop("Loan_ID", axis=1, inplace=True)
if choice == "Home":
st.write("Nous avons develeopper pour ce projet un model de classification\
qui permet, sur la base de certaines variables, de determiner si oui ou non\
il est envisageable d'octroyer un pret bancaire a une tierce personne.")
st.subheader(":orange[__Presentation du jeu de donnee__] :memo:")
st.markdown("Le jeu de donnees comporte 614 lignes et 13 colonnes. **Loan_Status**\
est la variables a predire (categorielle a deuc classe: **Y** pour le pret a ete \
octroyer et **N**) pour le contraire. afin d'avoir les reultats les plus\
optimaux possibles, nous allons dans un premier temps faire une \
***Analyse exploratoire** de nos donnees. Par suite nous passerons\
a la phase de preparation des donnees pour afin finir avec \
la phase de creation et optimisation des models.\
`Si vous televerser un fichier au format csv, vous avez la\
possibilite de comparer les prediction pour chaque\
model et de telechager le fichier csv correspondant.`")
#st.image("./images/processor.jpg")
if choice == "Data Exploration":
st.subheader(":orange[_Data Exploration_] :bar_chart:")
# afficher les donnees
st.write(data.head())
# valeurs manquante
if st.sidebar.checkbox("Valeur Manquante"):
st.subheader(":orange[Valeur Manquante]")
na_count = data.isnull().sum().to_frame(name='count')
na_per = (data.isnull().sum().to_frame(name='percentage %')/data.shape[0]*100).round(2)
st.write(pd.concat([na_count, na_per], axis=1).sort_values(by='count', ascending=False).T)
# valeur unique par colonne
if st.sidebar.checkbox("Valeur Unique par colonnes"):
st.subheader(":orange[Valeur Unique par colonnes]")
only = data.nunique().sort_values(ascending=False).to_frame(name='count')
perc = (data.nunique().sort_values(ascending=False).to_frame(name='percentage %')/data.shape[0]*100).round(2)
dtype = data.dtypes.to_frame(name='dtypes')
st.write(pd.concat([only, perc, dtype], axis=1).T)
# statistique sommaire
if st.sidebar.checkbox("Statistiques somaire"):
st.subheader(":orange[Statistiques sommaire]")
st.write(data.describe())
# matrice de correlation
if st.sidebar.checkbox("Matrice de correlation"):
fig = plt.figure(figsize=(7,5))
st.subheader(":orange[Matrice de correlation]")
st.write(sns.heatmap(data.corr(), annot=True, vmin=-1, vmax=1, cmap='ocean'))
st.pyplot(fig)
plt.show()
if choice == "Data Visualisation":
st.subheader(":orange[_Data Visualisation_] :chart:")
if st.sidebar.checkbox("Analyse Univariee"):
# selection des variables qualitatives
categorical_columns = data.select_dtypes(include='object').columns.tolist()
st.write("Liste des variables qaulitatives")
st.write(categorical_columns)
fig = plt.figure(figsize=(14, 8))
sns.set_theme(context='notebook', style='darkgrid', palette='deep', font='sans-serif', font_scale=1, color_codes=True, rc=None)
for idx, col in enumerate(categorical_columns[:-1]):
plt.subplot(2, 3, idx+1)
sns.countplot(data=data, x=col, hue="Loan_Status")
sns.countplot(data=data, x='Loan_Status')
st.pyplot(fig)
plt.show()
# selection des variables quantitatives
numerical_columns = data.select_dtypes(include='number').columns.tolist()
st.write("Liste des variables quantitatives")
st.write(numerical_columns)
fig = plt.figure(figsize=(15,7))
for idx, col in enumerate(numerical_columns):
plt.subplot(2,3, idx+1)
plt.hist(data[col], density=True)
sns.kdeplot(data=data, x=col)
plt.title(col)
#plt.subplots_adjust(hspace=0.5)
plt.tight_layout(h_pad=2, w_pad=3., rect=(1,1,2,2))
st.pyplot(fig)
plt.show()
if st.sidebar.checkbox("Analyse bivariee"):
st.subheader(":orange[Analyse bivariee]")
numerical_columns = data.select_dtypes(include='number').columns.tolist()
fig = plt.figure(figsize = (14, 8))
for idx, num_col in enumerate(numerical_columns[:-2]):
plt.subplot(2, 2, idx+1)
sns.boxplot(y=num_col, data=data, x='Loan_Status')
plt.tight_layout(h_pad=2, w_pad=3., rect=(1,1,2,2))
st.pyplot(fig)
plt.show()
if choice == "Make prediction":
st.subheader(":orange[Make prediction] :fleur_de_lis:")
if uploaded_file is not None:
data = pd.read_csv(uploaded_file)
# data preprocessing
from sklearn.impute import SimpleImputer
try:
data.drop(["Loan_ID"], axis=1, inplace=True)
except:
pass
# encodage
data_encoded = pd.get_dummies(data, drop_first=True)
st.subheader(":orange[Donnees encodees]")
st.write(data_encoded)
# separation du jeu de donnee
if data_encoded.shape[1] == 15:
X, y = data_encoded.drop(["Loan_Status_Y"], axis=1), data_encoded["Loan_Status_Y"]
else:
X = data_encoded
# traintement des valeurs manquantes
sp = SimpleImputer(strategy="most_frequent")
X = sp.fit_transform(X)
# mis a l'echelle des variables
std = StandardScaler()
X = std.fit_transform(X)
# Prediction
# Random Forest predictor
if st.sidebar.checkbox("Random Forest"):
st.subheader(":orange[Random Forest] :sunglasses:")
rf = pickle.load(open("scoring_rf.pkl", "rb"))
pred = rf.predict(X)
pred_proba = rf.predict_proba(X)
st.subheader(':green[Prediction]')
loan_status = np.array(['N','Y'])
prediction = pd.DataFrame(loan_status[pred], columns=['prediction'])
df = pd.concat([data, prediction], axis=1)
st.write(df)
# download frame
csv = convert_df_to_csv(df)
st.download_button("Press to Download",
csv,
"random_forest.csv",
"text/csv",
key='rf_download_csv')
# Accuracy score
if data_encoded.shape[1] == 15:
st.text("Model report : \n " + classification_report(y, pred))
rf_score = accuracy_score(pred,y)
st.write(":green[score d'exactitude]")
st.write(f"{round(rf_score*100,2)}% d'exactitude")
st.subheader(':green[Prediction Probability]')
st.write(pred_proba)
# Linear Discriminant Analysis
if st.sidebar.checkbox("Discriminant Analysis"):
st.subheader(":orange[Discriminant Analysis] :sunglasses:")
lda = pickle.load(open("scoring_lda.pkl", "rb"))
pred = lda.predict(X)
pred_proba = lda.predict_proba(X)
st.subheader(':green[Prediction]')
loan_status = np.array(['N','Y'])
prediction = pd.DataFrame(loan_status[pred], columns=['prediction'])
df = pd.concat([data, prediction], axis=1)
st.write(df)
# download
csv = convert_df_to_csv(df)
st.download_button("Press to Download",
csv,
"discriminant.csv",
"text/csv",
key='lda_download_csv')
#st.text("Model report : \n " + classification_report(y, pred))
if data_encoded.shape[1] == 15:
st.text("Model report : \n " + classification_report(y, pred))
# Accuracy score
lda_score = accuracy_score(pred,y)
st.subheader(":green[score d'exactitude]")
st.write(f"{round(lda_score*100,2)}% d'exactitude")
st.subheader(':green[Prediction Probability]')
st.write(pred_proba)
if data_encoded.shape[1] == 15:
# matrice de confusion
fig = plt.figure(figsize=(2,1))
cm = confusion_matrix(y, pred)
st.subheader(":green[Matrice de confusion]")
sns.heatmap(cm, annot=True, cmap='Dark2')
st.pyplot(fig)
plt.plot()
# XGBoost
if st.sidebar.checkbox("XGBoost"):
st.subheader(":orange[XGBoost] :sunglasses:")
xg = xgb.XGBClassifier()
xg.load_model("xg.json")
pred = xg.predict(X)
pred_proba = xg.predict_proba(X)
st.subheader(':green[Prediction]')
loan_status = np.array(['N','Y'])
prediction = pd.DataFrame(loan_status[pred], columns=['prediction'])
df = pd.concat([data, prediction], axis=1)
st.write(df)
# download
csv = convert_df_to_csv(df)
st.download_button("Press to Download",
csv,
"xgboost.csv",
"text/csv",
key='xg_download_csv')
#st.text("Model report : \n " + classification_report(y, pred))
if data_encoded.shape[1] == 15:
st.text("Model report : \n " + classification_report(y, pred))
# Accuracy score
xg_score = accuracy_score(pred,y)
st.subheader(":green[score d'exactitude]")
st.write(f"{round(xg_score*100,2)}% d'exactitude")
st.subheader(':green[Prediction Probability]')
st.write(pred_proba)
# ANN
if st.sidebar.checkbox("Neural Network"):
st.subheader(":orange[Neural Network] :sunglasses:")
ann = load_model("ann.h5")
pred_proba = ann.predict(X)
pred = np.where(pred_proba < 0.5, 0, 1)
st.subheader(':green[Prediction]')
loan_status = np.array(['N','Y'])
prediction = pd.DataFrame(loan_status[pred], columns=['prediction'])
df = pd.concat([data, prediction], axis=1)
st.write(df)
# download
csv = convert_df_to_csv(df)
st.download_button("Press to Download",
csv,
"neural_network.csv",
"text/csv",
key='ann_download_csv')
#st.text("Model report : \n " + classification_report(y, pred))
if data_encoded.shape[1] == 15:
st.text("Model report : \n " + classification_report(y, pred))
# Accuracy score
ann_score = accuracy_score(pred,y)
st.subheader(":green[score d'exactitude]")
st.write(f"{round(ann_score*100,2)}% d'exactitude")
st.subheader(':green[Prediction Probability]')
un = pd.DataFrame(pred_proba, columns=['1'])
zero = pd.DataFrame(np.subtract(1, pred_proba), columns=['0'])
st.write(pd.concat([zero, un], axis=1).round(2))
else:
def user_input_features():
gender = st.sidebar.selectbox('Gender',('Male','Female'))
married = st.sidebar.selectbox('Married',('Yes','No'))
depedents = st.sidebar.selectbox('Dependent',(0, 1, 2, "3+"))
education = st.sidebar.selectbox('Education',('Graduate','Not Graduate'))
self_employed = st.sidebar.selectbox('Self_employed',('Yes','No'))
applicanincome = st.sidebar.slider('ApplicanIncome', 150, 81000)
coapplicanincome = st.sidebar.slider('CoapplicanIncome', 0, 42000)
loan_amount = st.sidebar.slider('LoanAmount', 0, 800)
loan_amount_term = st.sidebar.slider('Loan_Amount_Term', 10, 500)
credit_history = st.sidebar.selectbox('Credi_History', (0, 1))
property_area = st.sidebar.selectbox('Property_Area', ("Urban", "Rural", "Semiurban"))
if gender == "Male":
gender = 1
else:
gender = 0
if married == 'Yes':
married = 1
else:
married = 0
depedents_1, depedents_2, depedents_3 = 0,0,0
if depedents == 1:
depedents_1=1
elif depedents == 2:
depedents_2=1
elif depedents > 2 :
depedents_3=1
if education == "Not Graduate":
education=1
else:
education=0
if self_employed == "Yes":
self_employed = 1
else:
self_employed = 0
property_urban, property_semiurban = 0, 0
if property_area == "Semiurban":
property_semiurban = 1
elif property_area == "Urban":
property_urban == 1
data = { 'ApplicationIncome': (applicanincome - 5403)/6109,
'CoapplicationIncome': (coapplicanincome - 1621) / 2926,
'LoanAmount': (loan_amount -146)/85,
'Loan_Amount_Term': (loan_amount_term - 342)/65,
'Credi_History': (credit_history -0.84)/0.35,
'Gender_Male': gender,
'Married_Yes': married,
'Depedents_1': depedents_1,
'Depedents_2': depedents_2,
'Depedents_3+': depedents_3,
'Education_Not_Graduate': education,
'Self_Employed_Yes': self_employed,
'Property_Area_Semiurban': property_semiurban,
'Property_Area_Urban': property_urban
}
features = pd.DataFrame(data, index=[0])
return features
data_input = user_input_features()
# Random Forest
if st.sidebar.checkbox("Random Forest"):
st.subheader(":orange[Random Forest]")
rf = pickle.load(open("scoring_rf.pkl", "rb"))
pred = rf.predict(data_input)
if pred == 1:
st.write(":orange[__Le pret peut etre octroyer__] :white_check_mark:")
else:
st.write(":red[__Desole,...__] :disappointed:")
pred_proba = rf.predict_proba(data_input)
loan_status = np.array(['N','Y'])
prediction = pd.DataFrame(loan_status[pred], columns=['prediction'])
df = pd.concat([data_input, prediction], axis=1)
st.write(df)
st.subheader(":green[probability] :question:")
st.write(pred_proba)
# Discriminant Analysis
if st.sidebar.checkbox("Discriminant Analysis"):
st.subheader(":orange[Discriminant Analysis]")
lda = pickle.load(open("scoring_lda.pkl", "rb"))
pred = lda.predict(data_input)
if pred == 1:
st.write(":orange[__Le pret peut etre octroyer__] :white_check_mark:")
else:
st.write(":red[__Desole,...__] :disappointed:")
pred_proba = lda.predict_proba(data_input)
loan_status = np.array(['N','Y'])
prediction = pd.DataFrame(loan_status[pred], columns=['prediction'])
df = pd.concat([data_input, prediction], axis=1)
st.write(df)
st.subheader(":green[probability] :question:")
st.write(pred_proba)
# XGboost
if st.sidebar.checkbox("XGBoost"):
st.subheader(":orange[XGBoost]")
xg = xgb.XGBClassifier()
xg.load_model("xg.json")
pred = xg.predict(data_input)
if pred == 1:
st.write(":orange[__Le pret peut etre octroyer__] :white_check_mark:")
else:
st.write(":red[__Desole,...__] :disappointed:")
pred_proba = xg.predict_proba(data_input)
loan_status = np.array(['N','Y'])
prediction = pd.DataFrame(loan_status[pred], columns=['prediction'])
df = pd.concat([data_input, prediction], axis=1)
st.write(df)
st.subheader(":green[probability] :question:")
st.write(pred_proba)
# ANN
if st.sidebar.checkbox("Neural Network"):
st.subheader(":orange[Neural Network]")
ann = load_model('ann.h5')
pred_proba = ann.predict(data_input)
pred = np.where(pred_proba < 0.5, 0, 1)
if pred == 1:
st.write(":orange[__Le pret peut etre octroyer__] :white_check_mark:")
else:
st.write(":red[__Desole,...__] :disappointed:")
loan_status = np.array(['N','Y'])
prediction = pd.DataFrame(loan_status[pred], columns=['prediction'])
df = pd.concat([data_input, prediction], axis=1)
st.write(df)
st.subheader(":green[probability] :question:")
un = pd.DataFrame(pred_proba, columns=['1'])
zero = pd.DataFrame(np.subtract(1, pred_proba), columns=['0'])
st.write(pd.concat([zero, un], axis=1).round(2))
# lancer l'application
if __name__ == "__main__":
main()
|