Objective: The project aimed to analyze a year's worth of sales data compiled from 12 separate CSV files to uncover insights into sales trends, customer behavior, and operational efficiencies. By cleaning, merging, and exploring this dataset, the goal was to answer specific business questions and support data-driven decision-making. The source of the data and the guiding questions is attributed to the repository: KeithGalli/Pandas-Data-Science-Tasks.
-
Data Integration: Aggregated data from 12 distinct CSV files into a single DataFrame to create a comprehensive dataset for analysis.
- Skill Highlight: Mastered advanced data cleaning techniques to ensure data accuracy and readiness for analysis.
-
Data Cleaning: Identified and removed any duplicate entries and handled missing values (NaNs) to improve dataset integrity.
- Skill Highlight: Ensured data coherence for analysis by merging multiple datasets and employing rigorous data cleaning methods.
-
Column Addition: Enhanced the dataset by creating new columns from existing data, enriching the dataset for deeper analysis.
- Skill Highlight: Boosted analytical depth by adding new columns and extracting new analytical dimensions from existing data.
-
Data Transformation: Applied transformations to parse strings, change data types, and utilize the
.apply()method for more complex data manipulations.- Skill Highlight: Streamlined data analysis and manipulation using functional transformation methods.
-
Business Question Analysis: Addressed high-level business questions through exploratory data analysis, leveraging Pandas and Matplotlib for insights.
- Skill Highlights: Revealed key trends and patterns through aggregate data analysis; uncovered and illustrated data insights with complex visualizations.
-
Visualization and Interpretation: Utilized bar charts, line graphs, and precise labeling to communicate findings effectively.
- Skill Highlights: Augmented communicative power of visualizations with precise labeling strategies; employed feature engineering and selection to boost predictive model efficacy.
some of the questiones that were used as guidance are from the repository listed above:
- What was the best month for sales? How much was earned that month?
- What city sold the most product?
- What time should we display advertisemens to maximize the likelihood of customer’s buying product?
- What products are most often sold together?
- What product sold the most? Why do you think it sold the most?
- Sales Trends: Identified the best performing months, cities with the highest sales, and optimal times for advertising to maximize customer purchases.
- Product Insights: Analyzed product sales to determine the most frequently sold products together and the top-selling product, exploring reasons behind sales trends.
Beyond the scope of predefined questions, the project also ventured into additional analyses, driven by curiosity and the potential for discovering untapped insights within the data.