def main():
st.title('MetMCC-SCAN')
st.header('A Predictor for Metastasis of Merkel Cell Carcinoma')
st.subheader("*Reducing Unnecessary Sentinel Lymph Node Biopsies*")
inputs = pd.DataFrame(get_sidebar_input(), index=[0])
# st.dataframe(inputs)
inputs = rename_categories(inputs)
# st.dataframe(inputs)
inputs = inputs[[
'AGE', 'SEX', 'PRIMARY_SITE', 'TUMOR_SIZE', 'DEPTH',
'LYMPH_VASCULAR_INVASION', 'TUMOR_INFILTRATING_LYMPHOCYTES',
'IMMUNE_SUPPRESSION', 'GROWTH_PATTERN', 'TUMOR_BASE_TRANSECTION'
]]
# st.dataframe(inputs)
if st.button("Predict"):
# load preprocessor
preprocessor = load_preprocessor()
inputs = preprocess(preprocessor, inputs)
# st.dataframe(inputs)
# load model
model = load_model()
y_prob = np.asarray(model.predict_proba(inputs))
y_pred = np.where(y_prob[:, 1] > config.THRESHOLD, 1, 0)
# output prediction
st.write("Probability of having a positive biopsy:", y_prob[:, 1][0])
local_css("style.css")
if y_pred[0] == 0:
t = '''<div>The patient is likely to have a
<span class='highlight blue'>negative </span>
Sentinel Lymph Node Biopsy result.
</div>
'''
else:
t = '''<div>The patient is likely to have a
<span class='highlight red'>positive </span>
Sentinel Lymph Node Biopsy result.
</div>
'''
st.markdown(t, unsafe_allow_html=True)
st.markdown("""<br>""", unsafe_allow_html=True)
image = Image.open('./image/lymph_nodes.jpg')
st.image(image, use_column_width=True)
import pandas as pd
import numpy as np
import joblib
from pickle5 import pickle
from PIL import Image
import torch
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
from transformers import AutoModelForSequenceClassification, AutoTokenizer
from sentence_transformers import SentenceTransformer, util
#streamlit
import streamlit as st
import SessionState
from load_css import local_css
local_css("./streamlit/style.css")
DEFAULT = '< PICK A VALUE >'
def selectbox_with_default(text, values, default=DEFAULT, sidebar=False):
func = st.sidebar.selectbox if sidebar else st.selectbox
return func(text, np.insert(np.array(values, object), 0, default))
#helper functions
from inspect import getsourcefile
import os.path as path, sys
current_dir = path.dirname(path.abspath(getsourcefile(lambda: 0)))
sys.path.insert(0, current_dir[:current_dir.rfind(path.sep)])
import src.clean_dataset as clean
body {
background-image: url("data:image/png;base64,%s");
background-size: cover;
}
</style>
''' % bin_str
st.markdown(page_bg_img, unsafe_allow_html=True)
return
set_png_as_page_bg('robo1.0.jpeg')
from load_css import local_css
local_css("styles.css")
t = "<div class='bold highlight'>Facial Emotion Detection</div>"
st.markdown(t, unsafe_allow_html=True)
def recog():
cap = cv2.VideoCapture(0)
while True:
# Grab a single frame of video
ret, frame = cap.read()
labels = []
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_classifier.detectMultiScale(gray, 1.3, 5)
#APP STREAMLIT : (commande : streamlit run XX/dashboard.py depuis le dossier python)
import streamlit as st
import pandas as pd
import numpy as np
from pathlib import Path
import matplotlib.pyplot as plt
import seaborn as sns
from PIL import Image
from load_css import local_css
st.set_option('deprecation.showPyplotGlobalUse', False)
FILE_PATH = str(Path()) + "/data/dataframe_pred.csv"
local_css("style.css")
t = "<div><span class='title'>Dashboard de Demande de Prêt</div>"
st.markdown(t, unsafe_allow_html=True)
#st.title('Dashboard de Demande de Prêt')
#local_css("style.css")
#t = "<div>Hello there my <span class='highlight green'>name <span class='bold'>yo</span> </span> is <span class='highlight purple'>Fanilo <span class='bold'>Name</span></span></div>"
#st.markdown(t, unsafe_allow_html=True)
@st.cache
def load_data(nrows):
data = pd.read_csv(FILE_PATH, nrows=nrows)
return data
import streamlit as st
import pandas as pd
import numpy as np
import popular_reco
from load_css import local_css
import readdata
local_css('style.css')
with st.spinner('Wait for song data to load ...'):
song_data = readdata.read_data_gdrive('song_data_with_gender.csv')
st.success('song data loaded')
with st.spinner('Wait for count data to load ...'):
count_data = readdata.read_data_gdrive('count_data.pkl')
st.success('count data loaded')
with st.spinner('Wait for imdb_merge data to load ...'):
song_imdb_merge = readdata.read_data_gdrive('song_only_imdb_merge.pkl')
st.success('imdb_merge data loaded')
def pass_song_data():
return song_data
def pass_count_data():
return count_data
f"""
<style>
.reportview-container {{
background: url(data:image/{main_bg_ext};base64,{base64.b64encode(open(main_bg, "rb").read()).decode()})
}}
.sidebar .sidebar-content {{
background: url(data:image/{side_bg_ext};base64,{base64.b64encode(open(side_bg, "rb").read()).decode()})
}}
</style>
""",
unsafe_allow_html=True
)
lcss.local_css("style.css")
t = "<div><span class='highlight red'> <span class='bold'>Machine Learning GUI Project</span></span></div>"
st.markdown(t, unsafe_allow_html=True)
learning_option = st.sidebar.selectbox(
'Select Learning Algorithm',
('Supervised Learning', 'Unsupervised Learning')
)
# Core Packages
import streamlit as st
import helper
from load_css import local_css
local_css("css/style.css")
# NLP Packages
import numpy as np
import csv
import spacy_streamlit
import spacy
nlp = spacy.load('en_core_web_sm')
def main():
st.markdown(title_temp, unsafe_allow_html=True)
menu = ['Detection', 'Counselling', 'Are you Mentally Ill?']
choice = st.sidebar.selectbox('Menu', menu)
if choice == 'Detection':
st.subheader('Detecting Offensive Words')
user_input = st.text_input("Message: ")
words = user_input.split()
clean = []
foul = []
for word in words:
word = word.lower()
temp = helper.calc_thresold(word)
if (temp['bad'] > temp['good']) and temp['bad'] > 0.65:
import typing
from PIL import Image
# Project Modules
from torchvision.transforms import transforms
from src.model.FaceNet import FaceNet
# Streamlit Imports
import streamlit as st
import load_css
# Pytorch
import torch
load_css.local_css("style.css")
st.title('Face Recognition Application')
PRETRAINED_MODEL_PATH = Path("pretrained_model/model")
ANCHOR_EMBEDDING_PATH = Path("pretrained_model/anchor_embeddings")
TUTORIAL_ANCHOR = Path("demo_images/tutorial_anchor")
TUTORIAL_TEST = Path("demo_images/tutorial_test")
# Streamlit encourages well-structured code, like starting execution in a main() function.
def main():
# Sanity Checks
if not PRETRAINED_MODEL_PATH.is_file():
st.error('Please check the "pretrained_model" directory. The pre-trained model is missing or are renamed. '
'Check "pretrained_model/README.md"!')
import streamlit as st
import stapp # import top_pop_songs, top_rated_songs # import sub-module stapp
from load_css import local_css
import login
import popular_reco
import menu
from user_reg import register
from user_list import user_list
import content_reco
from senti_collection import top_senti_recommendation
from PIL import Image
from cf_user_item_reco import ui_recommendation
local_css("style.css") # include style.css
def print_hi(name):
welcome_head = f"<div>Hi <span class='highlight blue'>{name}</span>, Welcome!</div>"
st.markdown(welcome_head, unsafe_allow_html=True)
def main():
logo = Image.open('Dhwani Logo.png')
st.sidebar.image(logo)
st.header('Top Songs Recommender System')
yourname, yourpass, auth = login.login() #get login field values
if auth == 'authenticated': # display blocks below if authenticated
print_hi(yourname)
st.write('\n')
menu_out = menu.menu()
if menu_out == 'Senti-Collections':
