🚀Purpose: Analyze sexual assault cases in India between 2001 and 2014. Highlight the most affected regions and key timeframes to support preventive efforts. Data Source:
♻️Dataset from Kaggle, covering crimes against women across multiple states and union territories. Key Objectives:
🔍Identify trends in rape cases and compare with other crimes against women. Highlight districts and states with significant concerns. Data Structure:
❕Columns include: State/UT, District, Year, and several crime categories like Rape, Kidnapping, Dowry Deaths, Outraging Modesty, etc. The dataset spans 2001–2014. Data Cleaning:
Duplicate removal, handling missing values, renaming columns, and converting data types for consistency. Exploratory Data Analysis (EDA):
◻️Summarizing data with statistics, identifying trends through visualizations, and detecting outliers. Visualization Techniques:
📈📉Line Charts for time-series trends. Bar Plots for comparing categories. Pie Charts for proportional representations. Findings and Conclusion:
🎗️Identified key trends and regions with concerns. Policy recommendations for women’s safety. Suggestions for future research and deeper insights.
🥀
🍁🎗️ Start: Data Source Objective: Analyze crime trends over time.
🌊Data Cleaning Process Remove duplicates: Eliminate any redundant entries in the dataset to avoid skewed analysis. Handle missing data: Address missing values using techniques like imputation or removing incomplete rows. Rename columns: Ensure all column names are descriptive and consistent for easier interpretation. Convert data types: Convert columns into appropriate data types (e.g., date, numeric, categorical) to facilitate further analysis.
🗝️📈📉Exploratory Data Analysis (EDA) Summarize data: Provide descriptive statistics like mean, median, mode, etc., to understand data distribution. Visualize trends: Use graphical techniques such as histograms or scatter plots to reveal patterns and relationships. Detect outliers: Identify any unusual data points that may require special attention or removal.
🚀Trend Identification & Visualization Techniques Line Charts (Time-Series): Visualize changes in crime over time, detecting patterns or spikes in certain years. Bar Plots (Category-wise): Compare crime occurrences across different categories such as types of crime or regions. Pie Charts (Proportions): Display proportions of various crime types or categories within the dataset.
🥀Conclusion & Recommendations Key trends identified: Summarize the most significant findings from the analysis (e.g., rise or fall in certain crime types). Regional analysis: Identify regions with higher crime rates or specific trends. Policy suggestions: Provide actionable recommendations to policymakers for reducing crime based on the analysis.
🔍Future Research: Suggest areas where further investigation is required, such as newer datasets, deeper regional analysis, or integrating socio-economic factors to better understand crime drivers.
🔥
Our project focuses on analyzing State/UT-wise Sexual Assault Data in India from 2001 to 2014. It aims to uncover patterns in crimes against women, focusing on sensitive regions and critical periods. By using data visualization techniques, the research offers insights into trends and provides recommendations for advocacy, policy decisions, and preventive measures.
