Delete pages
Browse files- pages/1 Problem Statement.py +0 -36
- pages/2 Data Understanding.py +0 -38
- pages/pages/3 EDA.py +0 -32
pages/1 Problem Statement.py
DELETED
|
@@ -1,36 +0,0 @@
|
|
| 1 |
-
import streamlit as st
|
| 2 |
-
|
| 3 |
-
# π Problem Statement
|
| 4 |
-
st.markdown("""
|
| 5 |
-
## π Problem Statement
|
| 6 |
-
|
| 7 |
-
Industrial and residential projects often face uncertainties and environmental risks during planning and execution.
|
| 8 |
-
Failing to assess risk levels early can lead to project delays, increased costs, and environmental concerns.
|
| 9 |
-
|
| 10 |
-
There is a growing need for a reliable, data-driven approach to evaluate risk levels based on project features like location, budget, team size, and environmental factors.
|
| 11 |
-
|
| 12 |
-
""")
|
| 13 |
-
|
| 14 |
-
# π― Objective
|
| 15 |
-
st.markdown("""
|
| 16 |
-
## π― Objective
|
| 17 |
-
|
| 18 |
-
This project aims to:
|
| 19 |
-
|
| 20 |
-
- π§ Develop a Machine Learning model using **Random Forest Classifier** to classify projects into **Low**, **Medium**, or **High Risk**.
|
| 21 |
-
- π Provide an intuitive **Streamlit web application** to allow users to input key project parameters and receive instant risk classification.
|
| 22 |
-
- β οΈ Help stakeholders make **informed decisions** by understanding potential risk levels in advance.
|
| 23 |
-
- π§ͺ Demonstrate the end-to-end pipeline of a classification problem including **data preprocessing**, **model building**, and **deployment**.
|
| 24 |
-
|
| 25 |
-
### π§© Why is this important?
|
| 26 |
-
|
| 27 |
-
- β
Promotes **early risk detection** and **preventive planning**.
|
| 28 |
-
- β
Supports data-driven decisions in urban and industrial development.
|
| 29 |
-
- β
Demonstrates real-world use of **ML classification** in project management.
|
| 30 |
-
""")
|
| 31 |
-
|
| 32 |
-
if st.button('Next'):
|
| 33 |
-
st.switch_page(r"pages\2.Data Understanding.py")
|
| 34 |
-
|
| 35 |
-
if st.button('Back'):
|
| 36 |
-
st.switch_page(r"app.py")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pages/2 Data Understanding.py
DELETED
|
@@ -1,38 +0,0 @@
|
|
| 1 |
-
import streamlit as st
|
| 2 |
-
|
| 3 |
-
# π₯ Data Collection & Understanding
|
| 4 |
-
st.markdown("""
|
| 5 |
-
## π₯ Data Collection & Data Understanding
|
| 6 |
-
|
| 7 |
-
### π¦ Data Collection:
|
| 8 |
-
|
| 9 |
-
The dataset used in this project was sourced from a structured collection of industrial and residential project data.
|
| 10 |
-
It includes various **environmental**, **team-related**, and **budget-related attributes** that influence the overall risk level of a project.
|
| 11 |
-
|
| 12 |
-
### π Dataset Features:
|
| 13 |
-
|
| 14 |
-
- **Project Type**: Type of the project (e.g., Construction, IT, Manufacturing, etc.)
|
| 15 |
-
- **Team Size**: Number of people working on the project
|
| 16 |
-
- **Project Budget (USD)**: Total budget allocated to the project in U.S. dollars
|
| 17 |
-
- **Estimated Timeline (Months)**: Duration estimated to complete the project
|
| 18 |
-
- **Complexity Score**: A numerical value representing the technical and operational complexity of the project
|
| 19 |
-
- **Stakeholder Count**: Number of stakeholders involved in decision-making
|
| 20 |
-
- **Methodology Used**: Project management approach adopted (e.g., Agile, Waterfall)
|
| 21 |
-
- **Team Experience Level88: Average experience level of the team (e.g., Junior, Mid, Senior)
|
| 22 |
-
- **External Dependencies Count**: Number of third-party or external factors the project relies on
|
| 23 |
-
- **Requirement Stability**: Indicates how frequently the project requirements change (e.g., Stable, Unstable)
|
| 24 |
-
- **Current Phase Duration (Months)**: Time spent in the current project phase
|
| 25 |
-
- **Risk Level (Target)**: The overall predicted risk level of the project (Low, Medium, High)
|
| 26 |
-
|
| 27 |
-
### π Key Understanding:
|
| 28 |
-
|
| 29 |
-
- **Data Type**: A mix of **categorical** and **numerical** features
|
| 30 |
-
- **Data Size**: Moderate-sized dataset suitable for training classification models
|
| 31 |
-
- **Target Variable**: **Risk Level** β classified as **Low**, **Medium**, or **High** based on the input attributes
|
| 32 |
-
""")
|
| 33 |
-
|
| 34 |
-
if st.button('Next'):
|
| 35 |
-
st.switch_page(r"pages\3.EDA.py")
|
| 36 |
-
|
| 37 |
-
if st.button('Back'):
|
| 38 |
-
st.switch_page(r"pages\1.Problem Statement.py")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
pages/pages/3 EDA.py
DELETED
|
@@ -1,32 +0,0 @@
|
|
| 1 |
-
import streamlit as st
|
| 2 |
-
|
| 3 |
-
st.markdown("""
|
| 4 |
-
## π Exploratory Data Analysis (EDA)
|
| 5 |
-
|
| 6 |
-
### π Data Exploration:
|
| 7 |
-
|
| 8 |
-
The dataset was thoroughly explored to understand patterns and relationships among the features that contribute to project risk.
|
| 9 |
-
The focus was on identifying which factors most influence whether a project is categorized as **Low**, **Medium**, or **High Risk**.
|
| 10 |
-
|
| 11 |
-
### π Key Observations:
|
| 12 |
-
|
| 13 |
-
- Projects with **high pollution levels** and **low green space** were more likely to fall under **High Risk**
|
| 14 |
-
- A **smaller distance to industrial areas** significantly increased the risk classification
|
| 15 |
-
- **Large team sizes** with insufficient environmental planning showed a trend toward higher risk
|
| 16 |
-
- **Project type** played a major role, with construction and manufacturing projects being riskier on average
|
| 17 |
-
|
| 18 |
-
### π Visualization Techniques:
|
| 19 |
-
|
| 20 |
-
- **Countplots** to visualize the distribution of categorical variables like project type and risk level
|
| 21 |
-
- **Boxplots** to analyze budget and team size across different risk levels
|
| 22 |
-
- **Heatmaps** to study correlations among features and the target (risk level)
|
| 23 |
-
- **Pairplots** for a multivariate look at environmental and internal features
|
| 24 |
-
|
| 25 |
-
These insights were crucial in **feature selection** and helped improve model accuracy during the training phase.
|
| 26 |
-
""")
|
| 27 |
-
|
| 28 |
-
if st.button('Next'):
|
| 29 |
-
st.switch_page(r"pages\4.Feature Engineering.py")
|
| 30 |
-
|
| 31 |
-
if st.button('Back'):
|
| 32 |
-
st.switch_page(r"pages\2.Data Understanding.py")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|