similarité

App/utils/divers_function.py

@@ -1,5 +1,12 @@
 import streamlit as st
 import pandas as pd
+import re
+from App.utils.standadisation import *
+from nltk.corpus import stopwords
+from nltk.stem import PorterStemmer
+from nltk.stem.snowball import FrenchStemmer
+from nltk.corpus import stopwords
+
 
 @st.cache_data
 def convert_df(df):
@@ -20,8 +27,6 @@ def supprime_country(df):
     return df
 
 
-
-
 def Merger(df, data_tr, produit_id, class_id):
     keys = data_tr[produit_id].unique()
     df_finale_v1 = df[df[produit_id].isin(keys)]
@@ -34,6 +39,77 @@ def Merger(df, data_tr, produit_id, class_id):
     
     # Filtrer les lignes où 'class_id' a été modifié
     merged_df = merged_df[merged_df[f'old_{class_id}'] != merged_df[f'{class_id}_y']]
-    finale_df = merged_df[["COUNTRY_KEY", "ITEM_DESC_x",f"old_{class_id}",f'{class_id[:-4]}_DESC_FR_x', f'{class_id}_y',  f'{class_id[:-4]}_DESC_FR_y',"ITEM_DESC_y","nombre","total_by_ligne", "Proportion", "Countries"]]
+    finale_df = merged_df.drop(["_merge"], axis = 1) #[["COUNTRY_KEY" ,produit_id,"ITEM_DESC_x",f"old_{class_id}",f'{class_id[:-4]}_DESC_FR_x', f'{class_id}_y',  f'{class_id[:-4]}_DESC_FR_y',"ITEM_DESC_y","nombre","total_by_ligne", "Proportion", "Countries","Poids"]]
     return finale_df
 
+
+
+def data_cleaning(strings):
+
+    strings = strings.lower().strip()
+    strings = strings.replace('\'',' ')
+    strings = strings.replace('/',' ')
+    strings = re.sub(r'[^\w\s]', ' ', strings)
+    text_normalized = re.sub('[^A-Za-z ,éêèîôœàâ]+', ' ', strings)
+
+    return text_normalized
+
+
+def standardization(strings):
+  liste = strings.split(' ')
+  for i in range(len(liste)) :
+    if liste[i] in dictionnaire.keys():
+      liste[i] = dictionnaire[liste[i]]
+  return ' '.join(liste)
+
+
+def remove_stop_words(strings):
+    liste_stopword_unicode = [str(item) for item in liste_stopword]
+    en_stops = set(stopwords.words('english') + liste_stopword_unicode)
+    fr_stops = set(stopwords.words('french') + liste_stopword_unicode)
+
+    list_DESCRIPTION = strings.split(' ')
+    cleaned_list = []
+
+    for ingredient in list_DESCRIPTION:
+        temp = ingredient.split(' ')
+        cleaned_ingredient = ' '.join([word for word in temp if word.lower() not in en_stops])
+        cleaned_list.append(cleaned_ingredient)
+
+    strings = ' '.join([ingredient for ingredient in cleaned_list])
+    list_DESCRIPTION = strings.split(' ')
+    cleaned_list = []
+
+    for ingredient in list_DESCRIPTION:
+        temp = ingredient.split(' ')
+        cleaned_ingredient = ' '.join([word for word in temp if word.lower() not in fr_stops])
+        cleaned_list.append(cleaned_ingredient)
+
+    strings = ' '.join([ingredient for ingredient in cleaned_list])
+    return strings
+
+
+en_stemmer = PorterStemmer()
+fr_stemmer = FrenchStemmer()
+
+
+def stem_sentence(sentence, stemmer):
+    words = sentence.split(' ')
+    stemmed_words = [stemmer.stem(word) for word in words]
+    stemmed_sentence = ' '.join(stemmed_words)
+    return stemmed_sentence
+
+
+def english_stemmer(strings):
+    list_ingredients = strings.split(' ')
+    stemmed_list = [stem_sentence(ingredient, en_stemmer) for ingredient in list_ingredients]
+    strings = ' '.join(stemmed_list)
+    return strings
+
+
+def french_stemmer(strings):
+    list_ingredients = strings.split(',')
+    stemmed_list = [stem_sentence(ingredient, fr_stemmer) for ingredient in list_ingredients]
+    strings = ' '.join(stemmed_list)
+    return strings
+

App/utils/filter_dataframe.py

@@ -0,0 +1,86 @@
+import pandas as pd
+import streamlit as st
+from pandas.api.types import (
+    is_categorical_dtype,
+    is_datetime64_any_dtype,
+    is_numeric_dtype,
+    is_object_dtype,
+)
+
+
+
+def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Adds a UI on top of a dataframe to let viewers filter columns
+
+    Args:
+        df (pd.DataFrame): Original dataframe
+
+    Returns:
+        pd.DataFrame: Filtered dataframe
+    """
+    modify = st.checkbox("Add filters")
+
+    if not modify:
+        return df
+
+    df = df.copy()
+
+    # Try to convert datetimes into a standard format (datetime, no timezone)
+    for col in df.columns:
+        if is_object_dtype(df[col]):
+            try:
+                df[col] = pd.to_datetime(df[col])
+            except Exception:
+                pass
+
+        if is_datetime64_any_dtype(df[col]):
+            df[col] = df[col].dt.tz_localize(None)
+
+    modification_container = st.container()
+
+    with modification_container:
+        to_filter_columns = st.multiselect("Filter dataframe on", df.columns)
+        for column in to_filter_columns:
+            left, right = st.columns((1, 20))
+            left.write("↳")
+            # Treat columns with < 10 unique values as categorical
+            if is_categorical_dtype(df[column]) or df[column].nunique() < 10:
+                user_cat_input = right.multiselect(
+                    f"Values for {column}",
+                    df[column].unique(),
+                    default=list(df[column].unique()),
+                )
+                df = df[df[column].isin(user_cat_input)]
+            elif is_numeric_dtype(df[column]):
+                _min = float(df[column].min())
+                _max = float(df[column].max())
+                step = (_max - _min) / 100
+                user_num_input = right.slider(
+                    f"Values for {column}",
+                    _min,
+                    _max,
+                    (_min, _max),
+                    step=step,
+                )
+                df = df[df[column].between(*user_num_input)]
+            elif is_datetime64_any_dtype(df[column]):
+                user_date_input = right.date_input(
+                    f"Values for {column}",
+                    value=(
+                        df[column].min(),
+                        df[column].max(),
+                    ),
+                )
+                if len(user_date_input) == 2:
+                    user_date_input = tuple(map(pd.to_datetime, user_date_input))
+                    start_date, end_date = user_date_input
+                    df = df.loc[df[column].between(start_date, end_date)]
+            else:
+                user_text_input = right.text_input(
+                    f"Substring or regex in {column}",
+                )
+                if user_text_input:
+                    df = df[df[column].str.contains(user_text_input)]
+
+    return df

App/utils/login.py

@@ -1,163 +0,0 @@
-import streamlit as st
-import bcrypt
-import streamlit as st 
-import pandas as pd 
-from App.class_input_box.input_box import *
-from App.functions_rupture.functions_gestion import *
-from App.utils.divers_function import *
-from App.utils.login import *
-
-from streamlit_extras.chart_container import chart_container
-
-
-def hash_password(password):
-    salt = bcrypt.gensalt()
-    hashed_password = bcrypt.hashpw(password.encode('utf-8'), salt)
-    return hashed_password
-
-def validate_login(email, password):
-    state = SessionState.get(is_authenticated=False)
-    stored_email = "rupture-gestion"  # Example stored email
-    stored_password =hash_password("Carrefour123!")  # Example hashed password
-    
-    if email == stored_email and bcrypt.checkpw(password.encode('utf-8'), stored_password):
-        state.is_authenticated = True
-    
-    return state.is_authenticated
-
-def login_page(state):
-
-    email = st.text_input("Email")
-    password = st.text_input("Password",type="password") 
-
-    check_password = st.button('Login')
-
-    if check_password:
-        return validate_login(email,password)
-    return state.is_authenticated
-
-
-@st.cache(suppress_st_warning=True, allow_output_mutation=True)
-def main_() :
-
-    email, password, login = login_page()
-    
-    if login:
-        if validate_login(email, password):
-            st.sidebar.success("Login successful!")
-
-            st.title("Gestion des ruptures ")
-
-            input_box = InputsBox()
-            data = input_box.get_data()
-
-            try:
-                if data.shape[0] != 0 :
-                    st.header("Data")
-
-                    st.dataframe(data)
-
-                    "## Filters"
-
-                    col1, col2 = st.columns(2)
-
-                    with col1 :
-                        product_id = input_box.get_product_id()
-
-                    with col2 :
-                        class_id = input_box.get_class_id()
-
-                    col1, col2 = st.columns(2)
-
-                    with col1 :
-                        min_product_id = input_box.valid_produict_id()
-
-                    with col2 :
-                        vaind_class_id = input_box.valid_class_id()
-
-                    conditions = input_box.conditions()
-
-                    if st.button("RUN ", key="run_button"):
-                        data = valide_key(data, product_id, class_id, min_product_id, vaind_class_id )
-                        Country, merged = nouvelle_data(data, 
-                                                        str(product_id), 
-                                                        str(class_id))
-
-                        merged_final = finale_merged(merged, 
-                                                     Country, 
-                                                     product_id, 
-                                                     class_id)            
-
-                        if conditions["Show data with ratios"]:
-                            st.subheader("Show data with ratios")
-                            st.dataframe(merged_final)
-
-                            csv = convert_df(merged_final)
-                            st.download_button(label="Download data as CSV",
-                                               data=csv,
-                                               file_name='sample_df.csv',
-                                               mime='text/csv',)
-
-                        data_countries_ratio = cond_pays_proportion(merged_final, 
-                                                                    conditions["Number of countries"], 
-                                                                    conditions["Proportion"], 
-                                                                    product_id)
-
-                        df = supprime_country(data_countries_ratio)
-                        csv = convert_df(df)
-
-                        """## The data below is filtered as follows: """
-                        "- Number of countries greater than or equal to ", conditions["Number of countries"]
-                        "- The proportion with the highest ", class_id ," is greater than or equal to ",conditions["Proportion"]
-
-                        finale_df = Merger(data,
-                                           df, 
-                                           product_id, 
-                                           class_id)
-
-                        tab1, tab2 = st.tabs(["Data without decision-making", "Data with proposed changes"])
-
-                        with tab1 :
-                            st.subheader("Data without decision-making")
-                            st.dataframe(df)
-                            st.download_button(label="Download data as CSV",
-                                               data=csv,
-                                               file_name='sample_df.csv',
-                                               mime='text/csv',)
-
-                        with tab2 :
-                            st.subheader("Data with proposed changes")
-                            st.dataframe(finale_df)
-                            csv_f = convert_df(finale_df)
-                            st.download_button(label="Download data as CSV",
-                                                   data=csv_f,
-                                                   file_name='sample_df.csv',
-                                                   mime='text/csv',)
-
-                        "## Country priority "
-
-                        priority_data = cond_pays_priorite(merged_final, product_id)
-
-                        tab1, tab2 = st.tabs(["Data without decision-making", "Data with proposed changes"])
-
-                        with tab1 :
-                            st.subheader("Data without decision-making")
-                            st.dataframe(priority_data)
-                            csv_f = convert_df(priority_data)
-                            st.download_button(label="Download data as CSV",
-                                                   data=csv_f,
-                                                   file_name='sample_df.csv',
-                                                   mime='text/csv',)
-
-                        with tab2 :
-                            "to do"
-
-            except:
-                pass
-                st.write("An error occured. Please check your inputs.")
-
-        else:
-            st.error("Identifiant ou mot de passe incorrect !")
-
-if __name__ == "__main__":
-    main_()

App/utils/standadisation.py

@@ -0,0 +1,17 @@
+dictionnaire = {"rg": "rouge","rges" : "rouge","rge": "rouge", "rse": "rose" ,"rs" : "rose", "bl": "blanc", "bdx": "Bordeaux", 
+                "vdt": "vin de table", 'vdp': "vin de pays","blc": "blanc", "bib": "bag in box", "citr": "citron", "co": "coco", "gourm" : "gourmand",
+                "patis": "patisserie", "p'tits" : "petit", "p'tit": "petit","p tit": "petit",  "pt": "pepite", "rev": "revil","succ": "sucettes",
+                "succet": "sucettes", "chocohouse": "choco house", "sach": "sachet", "choc": "choco", "tab" : "tablette", "hte" : "haute",
+                "spagh" : "spaghetti", "scht": "sachet", "nr": "noir", "caf": "cafe","barr": "barre", "pces": "pieces","pc": "pieces", "acidu": "acidule","blnc": "blanc",
+                "frui" : "fruit", "gourman" : "gourmand","bte" : "boîte", "bt" : "boîte", "ptit": "petit", "corb": "corbeil","ptits": "petit", "pti": "petit", "nois": "noisette",
+                "poul": "poulain", "barq" : "barquette", "barqu" : "barquette", 'fizz': 'fizzy', "st": "saint", "mich": "michel", "cal" : "calendrier", "calend" : "calendrier",
+                "calendr" : "calendrier", "caram" : "caramel", "cava" : "cavalier", "har" : "haribo", 'choc' : "chocolat", "choco" :"chocolat", 'lt' : "lait", "choc'n" :"chocolat noir",
+                "choc n" :"chocolat noir", "degust" : "degustation", "degus" : "degustation", "bis" : "biscuit", "coffr" : "coffret", "coff" : "coffret", "conf" : "confiserie",
+                "confis" : "confiserie", "croco" : "crocodile", "dble" : "double", "dess" : "dessert", "doyp" : "doypack", "harib" : "harib" , "et" : "etui", "exc" : "excellence",
+                "excel" : "excellence", "frit" : "friture","fritu" : "friture","fritur" : "friture", "gd" : "grand",  "gr" : "grand",  "grd" : "grand",  "grchoc" : "grand chocolat", "lat" : "lait", 'ass' : "assorti", "assoti" :"assorti",
+                "noug" : "nougatine", "nougat" : "nougatine", "scht" : "sachet", "sct" : "secret", "cho" : "chocolat" , "bisc" : "biscuit", "am" : "amande", "liq" : "liqueur", "tabl" : "tablette","asst":"assorti",
+                 "tab" : "tablette", "bil" : "bille", "vali" : "valisette", "cda" : "chevaliers d argouges", "tub": "tubo", "gril" :"grille", "amandesgrilles" : "amandes grilles", "ball" : "ballotin",
+                 "piecestubo" : "pieces tubo"
+                }
+
+liste_stopword = ['oz', 'kg', 'g', 'lb', 'mg', 'l', 'cl', 'ml', 'tsp', 'tbsp', 'cm', 'x', 'cte', 'h',"unknown"]

app.py

@@ -4,7 +4,23 @@ import time
 from App.class_input_box.input_box import *
 from App.functions_rupture.functions_gestion import *
 from App.utils.divers_function import *
-from App.utils.login import *
+from App.utils.filter_dataframe import *
+from App.utils.filter_dataframe import *
+
+
+# Page configuration
+st.set_page_config(
+    page_title="Gestion des ruptures",
+    page_icon="logo.png",
+    layout="wide"
+)
+hide_streamlit_style = """
+            <style>
+                footer {visibility: hidden;}
+            </style>
+            """
+st.markdown(hide_streamlit_style, unsafe_allow_html=True)
+
 
 
 def app():
@@ -18,7 +34,7 @@ def app():
             if data.shape[0] != 0 :
                 st.header("Data")
 
-                st.dataframe(data)
+                st.dataframe(filter_dataframe(data))
 
                 "## Parameters"
 
@@ -181,13 +197,16 @@ def app():
 
         except:
             pass
-            st.error('This is an error', icon="🚨")
+            #st.error('This is an error', icon="🚨")
             st.info('Ensure that column names are capitalized and that product_id and class_id descriptions are present, as well as a country column.', icon="ℹ️")
 
 
 if __name__ == "__main__":
-    st.sidebar.markdown("# Example of input")
-    st.sidebar.markdown("[https://docs.google.com/spreadsheets/d/123hVTOFpBT-C6mCnrOBh8fFIhSi8FxiuyHZJAQu8bDc/edit#gid=1220891905](Dataset)")
+    lien_label = "# Example of input"
+    lien_url = "https://docs.google.com/spreadsheets/d/123hVTOFpBT-C6mCnrOBh8fFIhSi8FxiuyHZJAQu8bDc/edit#gid=1220891905"
+    lien_html = f'<a href="{lien_url}">{lien_label}</a>'
+
+    st.sidebar.markdown(lien_html, unsafe_allow_html=True)
     st.toast("Hello")
     time.sleep(.5)
     st.toast('An example of input is on the left')

pages/recherche.py

@@ -0,0 +1,33 @@
+import streamlit as st 
+import requests
+
+# Configuration
+st.set_page_config(
+    page_title="Recherche",
+    page_icon="logo.png", 
+     layout="wide", 
+     initial_sidebar_state="auto"
+
+)
+change_footer_style = """
+            <style>
+                #MainMenu {visibility: hidden;}
+                footer {visibility: hidden;}
+            </style>
+            """
+st.markdown(change_footer_style, unsafe_allow_html=True)
+
+
+def get_product_info(EAN):
+    url = f"https://world.openfoodfacts.org/api/v0/product/{EAN}.json"
+    response = requests.get(url)
+    if response.status_code == 200:
+        return response.json()
+    else:
+        return {"error": "Product not found"}
+
+# Test de la fonction
+EAN =st.text_input("EAN", '0737628064502') # remplacer par l'EAN du produit
+if EAN :
+    product_info = get_product_info(EAN)
+    st.json(product_info)

requirements.txt

@@ -5,4 +5,5 @@ streamlit==1.25.0
 streamlit_extras==0.3.0
 gunicorn
 nltk
-bcrypt
+bcrypt
+re

rupture

@@ -1 +0,0 @@
-Subproject commit a552d499acb5c1c855daf3e23e8d3582ec467f09