Python for Data Analysis with Practical Projects

collect data with pandas and numpy; read multiple csv files, handle paths with raw strings, concatenate into a final data frame for analysis, and support visualizations with matplotlib and seaborn.

Prepare your data for analysis by converting datetime to timestamp and deriving weekday, day, month, hour, and minute attributes, then store them in the dataframe for deeper insights.

Analyze monthly ride patterns using data grouping and Plotly visuals to identify the month with maximum rides, then explore daily journeys with histograms and distribution plots for insights.

Analyze Uber demand with a month-wise approach and histogram visualizations of daily rides. Leverage seaborn point plots for hours of the day versus latitude, with hue by weekday.

Group data by base and month, count occurrences, and visualize popular bases by month with line plots. Perform cross analysis with heatmaps, pivot tables, and a reusable heat map function.

Perform spatial analysis of Uber ride data by visualizing latitude and longitude with a heat map and grouping by coordinates to reveal Sunday patterns, including Midtown Manhattan.

Analyze Uber pickups in New York City from Jan to Jun 2015 by performing data preparation, deriving features, and visualizing monthly counts with a bar chart showing a steady rise.

Analyze rush in New York City by hour and by weekday using count plots and point plots, revealing morning and weekend rush in Uber pickups.

Analyze Uber jan-feb data to identify the base number with the most active bases and trips. Create a trips-per-vehicle feature, set date as index, and compare distributions with box plots.

Load and clean a data frame in a Jupyter notebook with pandas and numpy, perform pre-processing by filling missing values and filtering invalid rows to enable robust analysis and insights.

Analyze guests' origins through spatial analysis using choropleth maps and pie charts, comparing resort and city hotels, with data cleaned and filtered for non-cancelled bookings, revealing Portugal leads Europe.

Analyze hotel price variation by room type and month using box plots and line charts. Merge resort and city data to reveal mean nightly prices in euros and summer peaks.

Analyze distribution of hotel stays by market segment and hotel type using box plots, and visualize guest meal preferences with a donut chart, highlighting breakfast as the most popular.

Analyze the relationship between special requests and booking cancellations by customers through data exploration, pivot tables, and visualizations, including count plots and bar charts.

Identify the busiest month by analyzing arrival month counts, merging city and resort guest data, and visualizing trends with a line plot.

Clean and analyze hotel data by filtering valid bookings, computing total nights, and visualizing with bar plots and a market-segment pie chart to reveal online dominance.

Recap data cleaning and pre-processing, and visualize relationships with bar, pie, and box plots while analyzing hotel bookings, including price per night by market segment and room type.

Learn to read data from a SQLite database using Python, pandas, and sqlite3, load it into a dataframe, and perform initial analysis and visualization in a Jupyter notebook.

Learn to perform sentiment analysis on data with text blob and polarity. Read data from SQLite and CSV, clean text with regex, and build a word cloud for positive sentences.

Analyze negative sentiments and user behavior to inform Amazon product recommendations, using exploratory data analysis, grouping by user, and calculating counts, mean scores, and top purchases.

Analyze customer feedback by measuring text length distributions and data quality, then visualize with a box plot and score counts to reveal most ratings are five stars.

Prepare and clean data by converting text to lowercase, removing punctuation and stop words, and applying custom rules to enable accurate sentiment analysis and feature exploration.

Learn to prepare covid-19 data for analysis by importing pandas and visualization tools, listing data directories, and building a reusable read_data function to load multiple csv datasets into data frames.

Analyze covid-19 data to identify top countries by total cases, deaths, recovered, and active cases using a plotly treemap and track trends with a line plot over date.

Explore exploratory data analysis and visualization to compute population to test done ratio and compare deaths, recovered, and active cases across top 20 countries with bar and stacked charts.

Explore Covid-19 data analysis using heatmaps, treemaps, and bar charts to identify top 20 countries by total confirmed cases, deaths, active and recovered cases, and population to test ratio.

Perform in-depth covid data analysis with Python, using pie charts and bar charts to compare worst-affected countries and death-to-confirmed and death-to-recovered ratios.

Automate data analysis by building a country-aware function that filters a data frame and visualizes date-based trends for confirmed, deaths, recovered, and active cases using subplots.

Perform descriptive analysis on a bank personal loan dataset by reading data, preprocessing and removing id and zip code, and using five-point summaries and box plots to reveal distributions.

Develop data pre-processing skills by visualizing distributions via histograms, checking skewness with pandas, and cleaning data: impute negative experience values with the mean using numpy where and prepare for analysis.

Analyze correlations with a heat map and mitigate multicollinearity by dropping the experience column. Map education codes to labels and visualize education status among loan applicants with plotly pie chart.

Create an account holder category from securities and CD accounts, visualize the distribution with a Plotly pie chart, and highlight that 87% have neither while 3% hold both.

Automate customer analysis by income and education using a simple Python function, producing interactive visuals with Plotly box plots and distplots. Compare distributions for education status and personal loan status.

Iterate over the data frame columns such as security account, online, account holder category, and credit card to generate count plots by personal loan, automating category analysis.

Automate hypothesis testing on loan data with scatter plots and SciPy two-sample t-tests, comparing age, income, and family against personal loan, interpreting p-values at 0.05.