Add application file

Readme.md

@@ -0,0 +1,92 @@
+ntroduction
+
+The OperationalML App is a machine learning profiler application designed to help developers and data scientists optimize and improve the performance of their machine learning models. The app works by analyzing the input data and output predictions of a model, and providing insights and recommendations to improve its accuracy, speed, and efficiency.
+Functional Requirements
+Requirement 1: Upload Dataset
+
+The user should be able to upload a dataset to be analyzed by the OperationalML App. Upon uploading, the dataset should be stored locally and displayed to the user for review.
+
+python
+
+if choice == "Upload":
+    st.title("Upload Your Dataset")
+    file = st.file_uploader("Upload Your Dataset")
+    if file: 
+        df = pd.read_csv(file, index_col=None)
+        df.to_csv('dataset.csv', index=None)
+        st.dataframe(df)
+
+Requirement 2: Exploratory Data Analysis
+
+The user should be able to perform exploratory data analysis on the uploaded dataset. The app should use pandas_profiling to generate a report on the dataset and display it to the user.
+
+python
+
+if choice == "Profiling": 
+    st.title("Exploratory Data Analysis")
+    profile_df = df.profile_report()
+    st_profile_report(profile_df)
+
+Requirement 3: Modelling
+
+The user should be able to choose a target column from the uploaded dataset and run a machine learning model on it. The app should use pycaret for modelling and should allow the user to compare different models to choose the best one. The best model should be saved as a .pkl file.
+
+python
+
+if choice == "Modelling": 
+    chosen_target = st.selectbox('Choose the Target Column', df.columns)
+    if st.button('Run Modelling'): 
+        def Encoder(df):
+          columnsToEncode = list(df.select_dtypes(include=['category','object']))
+          le = LabelEncoder()
+          for feature in columnsToEncode:
+              try:
+                  df = le.fit_transform(df)
+              except:
+                  print('Error encoding '+feature)
+          return df
+        df.astype(float)
+        df.dropna(inplace=True)
+        setup(df, target=chosen_target)
+        setup_df = pull()
+        st.dataframe(setup_df)
+        best_model = compare_models()
+        compare_df = pull()
+        st.dataframe(compare_df)
+        save_model(best_model, 'best_model')
+
+Requirement 4: Download Model
+
+The user should be able to download the best model as a .pkl file for future use.
+
+python
+
+if choice == "Download": 
+    with open('best_model.pkl', 'rb') as f: 
+        st.download_button('Download Model', f, file_name="best_model.pkl")
+
+Non-Functional Requirements
+Requirement 1: Performance
+
+The OperationalML App should be able to analyze large datasets and run machine learning models efficiently, without causing significant delays or crashes.
+Requirement 2: User Interface
+
+The user interface of the OperationalML App should be user-friendly and intuitive, allowing users with limited technical knowledge to use the app without difficulty.
+Requirement 3: Security
+
+The OperationalML App should be secure and protect user data from unauthorized access or modification.
+System Requirements
+
+The OperationalML App requires the following system requirements:
+
+    Python 3.7 or higher
+    streamlit
+    plotly
+    pandas_profiling
+    pycaret
+    streamlit_pandas_profiling
+    scikit-learn
+
+Conclusion
+
+The OperationalML App is a machine learning profiler application designed to help developers and data scientists optimize and improve the performance of their machine learning models. The app is user-friendly,

app.py

@@ -0,0 +1,51 @@
+import streamlit as st
+import plotly.express as px
+#from pycaret.regression import setup, compare_models, pull, save_model, load_model
+import pandas_profiling
+from pycaret.classification import *
+import pandas as pd
+from streamlit_pandas_profiling import st_profile_report
+import os
+
+if os.path.exists('./dataset.csv'):
+    df = pd.read_csv('dataset.csv', index_col=None)
+else:
+    df = pd.DataFrame() # default dataframe if one has not been provided
+
+with st.sidebar:
+    st.image("https://www.onepointltd.com/wp-content/uploads/2020/03/inno2.png")
+    st.title("OperationalML")
+    choice = st.radio("Navigation", ["Upload","Profiling","Modelling", "Download"])
+    st.info("This project application helps you build and explore your data.")
+
+if choice == "Upload":
+    st.title("Upload Your Dataset")
+    file = st.file_uploader("Upload Your Dataset")
+    if file:
+        df = pd.read_csv(file, index_col=None)
+        df.to_csv('dataset.csv', index=None)
+        st.dataframe(df)
+
+if choice == "Profiling":
+    st.title("Exploratory Data Analysis")
+    profile_df = df.profile_report()
+    st_profile_report(profile_df)
+
+if choice == "Modelling":
+    chosen_target = st.selectbox('Choose the Target Column', df.columns)
+    if chosen_target and st.button('Run Modelling'):
+        setup(df, target=chosen_target, silent=True)
+        setup_df=pull()
+        
+        best_model = compare_models()
+        compare_df = pull()
+        save_model(best_model, 'best_model')
+        st.dataframe(compare_df)
+
+
+if choice == "Download":
+    if os.path.exists('best_model.pkl'):
+        with open('best_model.pkl', 'rb') as f:
+            st.download_button('Download Model', f, file_name="best_model.pkl")
+    else:
+        st.warning("No model has been saved yet. Please run modelling first.")

dataset.csv

@@ -0,0 +1,93 @@
+PassengerId,HomePlanet,CryoSleep,Cabin,Destination,Age,VIP,RoomService,FoodCourt,ShoppingMall,Spa,VRDeck,Name,Transported
+0001_01,Europa,False,B/0/P,TRAPPIST-1e,39.0,False,0.0,0.0,0.0,0.0,0.0,Maham Ofracculy,False
+0002_01,Earth,False,F/0/S,TRAPPIST-1e,24.0,False,109.0,9.0,25.0,549.0,44.0,Juanna Vines,True
+0003_01,Europa,False,A/0/S,TRAPPIST-1e,58.0,True,43.0,3576.0,0.0,6715.0,49.0,Altark Susent,False
+0003_02,Europa,False,A/0/S,TRAPPIST-1e,33.0,False,0.0,1283.0,371.0,3329.0,193.0,Solam Susent,False
+0004_01,Earth,False,F/1/S,TRAPPIST-1e,16.0,False,303.0,70.0,151.0,565.0,2.0,Willy Santantines,True
+0005_01,Earth,False,F/0/P,PSO J318.5-22,44.0,False,0.0,483.0,0.0,291.0,0.0,Sandie Hinetthews,True
+0006_01,Earth,False,F/2/S,TRAPPIST-1e,26.0,False,42.0,1539.0,3.0,0.0,0.0,Billex Jacostaffey,True
+0006_02,Earth,True,G/0/S,TRAPPIST-1e,28.0,False,0.0,0.0,0.0,0.0,,Candra Jacostaffey,True
+0007_01,Earth,False,F/3/S,TRAPPIST-1e,35.0,False,0.0,785.0,17.0,216.0,0.0,Andona Beston,True
+0008_01,Europa,True,B/1/P,55 Cancri e,14.0,False,0.0,0.0,0.0,0.0,0.0,Erraiam Flatic,True
+0008_02,Europa,True,B/1/P,TRAPPIST-1e,34.0,False,0.0,0.0,,0.0,0.0,Altardr Flatic,True
+0008_03,Europa,False,B/1/P,55 Cancri e,45.0,False,39.0,7295.0,589.0,110.0,124.0,Wezena Flatic,True
+0009_01,Mars,False,F/1/P,TRAPPIST-1e,32.0,False,73.0,0.0,1123.0,0.0,113.0,Berers Barne,True
+0010_01,Earth,False,G/1/S,TRAPPIST-1e,48.0,False,719.0,1.0,65.0,0.0,24.0,Reney Baketton,False
+0011_01,Earth,False,F/2/P,TRAPPIST-1e,28.0,False,8.0,974.0,12.0,2.0,7.0,Elle Bertsontry,True
+0012_01,Earth,False,,TRAPPIST-1e,31.0,False,32.0,0.0,876.0,0.0,0.0,Justie Pooles,False
+0014_01,Mars,False,F/3/P,55 Cancri e,27.0,False,1286.0,122.0,,0.0,0.0,Flats Eccle,False
+0015_01,Earth,False,F/4/P,55 Cancri e,24.0,False,0.0,1.0,0.0,0.0,637.0,Carry Hughriend,False
+0016_01,Mars,True,F/5/P,TRAPPIST-1e,45.0,False,0.0,0.0,0.0,0.0,0.0,Alus Upead,True
+0017_01,Earth,False,G/0/P,TRAPPIST-1e,0.0,False,0.0,0.0,0.0,0.0,0.0,Lyde Brighttt,True
+0017_02,Earth,False,F/6/P,55 Cancri e,14.0,False,412.0,0.0,1.0,0.0,679.0,Philda Brighttt,False
+0020_01,Earth,True,E/0/S,TRAPPIST-1e,1.0,False,0.0,0.0,0.0,0.0,0.0,Almary Brantuarez,False
+0020_02,Earth,True,E/0/S,55 Cancri e,49.0,False,0.0,0.0,0.0,0.0,0.0,Glendy Brantuarez,False
+0020_03,Earth,True,E/0/S,55 Cancri e,29.0,False,0.0,0.0,,0.0,0.0,Mollen Mcfaddennon,False
+0020_04,Earth,False,E/0/S,TRAPPIST-1e,10.0,False,0.0,0.0,0.0,0.0,0.0,Breney Jacostanley,True
+0020_05,Earth,True,E/0/S,PSO J318.5-22,1.0,False,,0.0,0.0,0.0,0.0,Mael Brantuarez,False
+0020_06,Earth,False,E/0/S,TRAPPIST-1e,7.0,False,0.0,0.0,0.0,0.0,0.0,Terta Mcfaddennon,False
+0022_01,Mars,False,D/0/P,TRAPPIST-1e,21.0,False,980.0,2.0,69.0,0.0,0.0,,False
+0024_01,Europa,True,C/2/S,TRAPPIST-1e,62.0,False,0.0,0.0,,0.0,0.0,Penton Fullided,True
+0025_01,Earth,False,F/6/S,TRAPPIST-1e,15.0,False,0.0,225.0,0.0,998.0,0.0,Karard Brookenson,False
+0026_01,Europa,False,C/0/P,55 Cancri e,34.0,False,22.0,6073.0,0.0,1438.0,328.0,Anyoni Unconary,False
+0028_01,Mars,False,F/8/P,TRAPPIST-1e,43.0,False,1125.0,0.0,136.0,48.0,0.0,Ceros Mare,False
+0030_01,Earth,False,G/4/S,TRAPPIST-1e,32.0,False,0.0,850.0,81.0,437.0,453.0,Ginia Morsentley,False
+0031_01,Mars,False,F/9/P,TRAPPIST-1e,47.0,False,214.0,0.0,1411.0,0.0,1229.0,Coobix Datie,True
+0031_02,Mars,False,F/9/P,TRAPPIST-1e,2.0,False,0.0,0.0,0.0,0.0,0.0,Cinets Datie,True
+0031_03,Mars,False,F/9/P,TRAPPIST-1e,20.0,False,,0.0,1750.0,990.0,0.0,Dontch Datie,True
+0034_01,Europa,True,D/1/S,55 Cancri e,28.0,False,0.0,0.0,0.0,0.0,0.0,Ziba Oingwhedly,True
+0035_01,Mars,False,D/1/P,55 Cancri e,23.0,False,784.0,964.0,0.0,951.0,0.0,Luse Butte,False
+0036_01,Earth,False,F/8/S,55 Cancri e,15.0,,0.0,492.0,48.0,20.0,401.0,Marina Leodger,False
+0038_01,Earth,False,F/10/S,55 Cancri e,20.0,False,554.0,195.0,0.0,2606.0,0.0,Loise Wheelez,False
+0039_01,Earth,True,G/1/P,55 Cancri e,30.0,False,0.0,0.0,,0.0,0.0,Jorgie Batthewitt,False
+0041_01,Earth,True,G/2/P,TRAPPIST-1e,17.0,False,0.0,0.0,0.0,0.0,0.0,Margia Moodsey,True
+0043_01,Europa,False,B/3/P,TRAPPIST-1e,45.0,False,0.0,164.0,45.0,2511.0,855.0,Ankalik Cylistrand,False
+0044_01,Earth,True,G/3/P,TRAPPIST-1e,55.0,False,0.0,0.0,0.0,0.0,0.0,Jodye Coopelandez,False
+0044_02,Earth,True,G/3/P,55 Cancri e,4.0,False,0.0,0.0,0.0,0.0,0.0,Kayne Coopelandez,True
+0044_03,Earth,True,G/3/P,PSO J318.5-22,21.0,False,0.0,0.0,0.0,0.0,0.0,Cassa Coopelandez,True
+0045_01,Mars,False,F/10/P,TRAPPIST-1e,21.0,False,970.0,0.0,180.0,0.0,64.0,Zelowl Chmad,False
+0045_02,Mars,True,F/10/P,,19.0,False,0.0,0.0,0.0,0.0,0.0,Mass Chmad,True
+0050_01,Earth,False,E/1/S,55 Cancri e,35.0,False,790.0,0.0,0.0,,0.0,Sony Lancis,False
+0051_01,Earth,False,E/2/S,TRAPPIST-1e,56.0,False,0.0,112.0,0.0,1379.0,127.0,Vivia Johnshines,False
+0052_01,Earth,False,G/6/S,TRAPPIST-1e,,False,4.0,0.0,2.0,4683.0,0.0,Elaney Hubbarton,False
+0053_01,Earth,False,F/11/S,TRAPPIST-1e,25.0,False,0.0,0.0,1938.0,0.0,1.0,Elson Hickerson,True
+0056_01,Europa,False,A/1/S,TRAPPIST-1e,2.0,False,0.0,0.0,0.0,0.0,0.0,Okulas Tractive,True
+0056_02,Europa,True,A/1/S,TRAPPIST-1e,38.0,False,0.0,0.0,0.0,0.0,0.0,Instab Tractive,True
+0056_03,Europa,False,A/1/S,TRAPPIST-1e,27.0,False,279.0,605.0,3374.0,286.0,3.0,Zinoces Tractive,True
+0058_01,Earth,True,G/7/S,PSO J318.5-22,36.0,False,0.0,0.0,0.0,0.0,0.0,Warry Ayalazquez,False
+0061_01,Earth,False,F/12/S,TRAPPIST-1e,22.0,False,45.0,1096.0,148.0,1377.0,1.0,Shanya Salez,False
+0062_01,Earth,False,F/13/S,TRAPPIST-1e,62.0,False,0.0,592.0,0.0,17.0,25.0,Sterry Greeves,False
+0064_01,Mars,True,F/14/S,TRAPPIST-1e,15.0,False,0.0,0.0,0.0,0.0,0.0,,True
+0064_02,,True,E/3/S,TRAPPIST-1e,33.0,False,0.0,0.0,,0.0,0.0,Colatz Keen,True
+0066_01,Earth,False,G/6/P,TRAPPIST-1e,62.0,False,1.0,153.0,197.0,0.0,460.0,Diandy Pecketton,False
+0067_01,Earth,True,G/10/S,PSO J318.5-22,0.0,False,0.0,0.0,0.0,0.0,0.0,Ninaha Leeves,True
+0067_02,Earth,False,G/10/S,TRAPPIST-1e,18.0,False,1.0,258.0,446.0,0.0,0.0,Celine Leeves,True
+0067_03,Earth,False,F/15/S,55 Cancri e,21.0,False,1946.0,37.0,0.0,0.0,24.0,Velyne Leeves,False
+0068_01,Mars,False,E/4/S,TRAPPIST-1e,,False,793.0,0.0,2.0,253.0,0.0,Cinst Binie,False
+0069_01,Earth,False,F/16/S,TRAPPIST-1e,42.0,False,887.0,0.0,9.0,6.0,0.0,,True
+0070_01,Earth,False,F/13/P,TRAPPIST-1e,19.0,False,190.0,0.0,5.0,1.0,726.0,Meremy Brighttt,False
+0071_01,Earth,False,F/14/P,TRAPPIST-1e,17.0,False,16.0,2165.0,0.0,0.0,52.0,Nelly Dillines,False
+0072_01,Earth,False,F/17/S,TRAPPIST-1e,14.0,False,0.0,1.0,0.0,0.0,1063.0,Thell Brantuarez,False
+0073_01,Mars,False,D/3/P,PSO J318.5-22,37.0,False,46.0,83.0,738.0,0.0,12.0,Gorn Make,False
+0074_01,Europa,False,C/3/S,TRAPPIST-1e,42.0,False,1.0,8397.0,0.0,0.0,506.0,Aldibah Mostedry,True
+0076_01,Mars,False,F/18/S,TRAPPIST-1e,27.0,False,147.0,0.0,1018.0,0.0,0.0,Conk Dal,True
+0077_01,Mars,False,F/15/P,TRAPPIST-1e,28.0,False,14.0,0.0,1295.0,0.0,0.0,Pon Blité,True
+0078_01,Europa,False,C/4/S,TRAPPIST-1e,38.0,False,0.0,5840.0,0.0,321.0,9654.0,Spuri Pokerheed,False
+0081_01,Earth,True,G/13/S,TRAPPIST-1e,13.0,False,0.0,0.0,0.0,0.0,0.0,Dellie Vinozarks,False
+0082_01,Mars,False,F/16/P,TRAPPIST-1e,42.0,False,7406.0,0.0,0.0,0.0,0.0,Totse Datte,False
+0082_02,Mars,True,F/16/P,TRAPPIST-1e,2.0,False,0.0,0.0,0.0,0.0,0.0,Eaturs Datte,True
+0082_03,Mars,False,F/16/P,TRAPPIST-1e,8.0,False,0.0,0.0,0.0,0.0,0.0,,True
+0084_01,Earth,False,G/14/S,TRAPPIST-1e,24.0,False,688.0,0.0,0.0,0.0,17.0,Coren Coopezmaney,True
+0085_01,Europa,True,C/5/S,TRAPPIST-1e,40.0,False,0.0,0.0,0.0,0.0,0.0,Furudah Ellcefulve,True
+0086_01,Earth,False,F/17/P,TRAPPIST-1e,43.0,False,211.0,0.0,0.0,638.0,513.0,Jodye Kinson,False
+0088_01,Mars,True,E/5/S,PSO J318.5-22,45.0,False,0.0,0.0,0.0,0.0,0.0,Stmeal Sacre,True
+0090_01,Earth,True,G/15/S,TRAPPIST-1e,35.0,False,0.0,0.0,0.0,0.0,0.0,Heremy Santry,True
+0091_01,Earth,True,G/16/S,TRAPPIST-1e,26.0,False,,0.0,0.0,0.0,0.0,Deanne Yorkland,True
+0091_02,Earth,False,F/20/S,TRAPPIST-1e,27.0,False,1.0,697.0,31.0,188.0,0.0,Tinez Yorkland,False
+0092_01,Earth,False,G/9/P,TRAPPIST-1e,19.0,False,0.0,0.0,670.0,1.0,34.0,Gracy Dunnisey,False
+0092_02,Earth,True,G/9/P,TRAPPIST-1e,0.0,False,0.0,0.0,,0.0,0.0,Stald Hewson,True
+0092_03,Earth,True,G/9/P,TRAPPIST-1e,3.0,False,0.0,0.0,0.0,0.0,0.0,Tiney Hewson,True
+0097_01,Europa,False,A/2/S,TRAPPIST-1e,54.0,False,0.0,1208.0,0.0,3.0,637.0,Alchium Fictful,False
+0098_01,Earth,False,G/11/P,TRAPPIST-1e,26.0,False,0.0,856.0,5.0,32.0,0.0,Doria Carezquez,False
+0098_02,Earth,False,G/11/P,TRAPPIST-1e,26.0,False,0.0,2811.0,957.0,0.0,87.0,Leence Carezquez,True
+0099_01,Earth,False,F/19/P,PSO J318.5-22,23.0,False,311.0,427.0,526.0,37.0,0.0,Aliey Leetersoney,False

requirements.txt

@@ -0,0 +1,154 @@
+alembic==1.8.1
+altair==4.2.0
+asttokens==2.0.8
+attrs==22.1.0
+backcall==0.2.0
+blinker==1.5
+blis==0.7.9
+Boruta==0.3
+cachetools==5.2.0
+catalogue==1.0.2
+certifi==2022.9.24
+charset-normalizer==2.1.1
+click==8.1.3
+cloudpickle==2.2.0
+colorama==0.4.6
+colorlover==0.3.0
+commonmark==0.9.1
+cufflinks==0.17.3
+cycler==0.11.0
+cymem==2.0.7
+databricks-cli==0.17.3
+debugpy==1.6.3
+decorator==5.1.1
+docker==6.0.0
+entrypoints==0.4
+executing==1.1.1
+Flask==2.2.2
+fonttools==4.38.0
+funcy==1.17
+future==0.18.2
+gensim==3.8.3
+gitdb==4.0.9
+GitPython==3.1.29
+greenlet==1.1.3.post0
+htmlmin==0.1.12
+idna==3.4
+ImageHash==4.3.1
+imbalanced-learn==0.7.0
+importlib-metadata==5.0.0
+ipykernel==6.16.2
+ipython==8.5.0
+ipywidgets==8.0.2
+itsdangerous==2.1.2
+jedi==0.18.1
+Jinja2==3.1.2
+joblib==1.2.0
+jsonschema==4.16.0
+jupyter_client==7.4.4
+jupyter_core==4.11.2
+jupyterlab-widgets==3.0.3
+kiwisolver==1.4.4
+kmodes==0.12.2
+lightgbm==3.3.3
+llvmlite==0.37.0
+Mako==1.2.3
+MarkupSafe==2.1.1
+matplotlib==3.5.3
+matplotlib-inline==0.1.6
+missingno==0.5.1
+mlflow==1.30.0
+mlxtend==0.19.0
+multimethod==1.9
+murmurhash==1.0.9
+nest-asyncio==1.5.6
+networkx==2.8.7
+nltk==3.7
+numba==0.54.1
+numexpr==2.8.3
+numpy==1.20.3
+oauthlib==3.2.2
+packaging==21.3
+pandas==1.5.1
+pandas-profiling==3.4.0
+parso==0.8.3
+patsy==0.5.3
+phik==0.12.2
+pickleshare==0.7.5
+Pillow==9.2.0
+plac==1.1.3
+plotly==5.10.0
+preshed==3.0.8
+prometheus-client==0.15.0
+prometheus-flask-exporter==0.20.3
+prompt-toolkit==3.0.31
+protobuf==3.20.3
+psutil==5.9.3
+pure-eval==0.2.2
+pyarrow==9.0.0
+pycaret==2.3.10
+pydantic==1.10.2
+pydeck==0.8.0b4
+Pygments==2.13.0
+PyJWT==2.6.0
+pyLDAvis==3.3.1
+Pympler==1.0.1
+pynndescent==0.5.7
+pyod==1.0.6
+pyparsing==3.0.9
+pyrsistent==0.18.1
+python-dateutil==2.8.2
+pytz==2022.5
+pytz-deprecation-shim==0.1.0.post0
+PyWavelets==1.4.1
+PyYAML==5.4.1
+pyzmq==24.0.1
+querystring-parser==1.2.4
+regex==2022.9.13
+requests==2.28.1
+rich==12.6.0
+scikit-learn==0.23.2
+scikit-plot==0.3.7
+scipy==1.5.4
+seaborn==0.12.1
+semver==2.13.0
+six==1.16.0
+sklearn==0.0
+smart-open==6.2.0
+smmap==5.0.0
+spacy==2.3.8
+SQLAlchemy==1.4.42
+sqlparse==0.4.3
+srsly==1.0.6
+stack-data==0.5.1
+statsmodels==0.13.2
+streamlit==1.13.0
+streamlit-pandas-profiling==0.1.3
+tabulate==0.9.0
+tangled-up-in-unicode==0.2.0
+tenacity==8.1.0
+textblob==0.17.1
+thinc==7.4.6
+threadpoolctl==3.1.0
+toml==0.10.2
+toolz==0.12.0
+tornado==6.2
+tqdm==4.64.1
+traitlets==5.5.0
+typing_extensions==4.4.0
+tzdata==2022.5
+tzlocal==4.2
+umap-learn==0.5.3
+urllib3==1.26.12
+validators==0.20.0
+visions==0.7.5
+waitress==2.1.2
+wasabi==0.10.1
+watchdog==2.1.9
+wcwidth==0.2.5
+websocket-client==1.4.1
+Werkzeug==2.2.2
+widgetsnbextension==4.0.3
+wordcloud==1.8.2.2
+yellowbrick==1.2.1
+zipp==3.10.0

test_dataset.csv

@@ -0,0 +1,2 @@
+col1,col2,col3
+1,2,3