Fundamentals of MIS midterm 1

Variable

A named container that stores a value for reuse, such as sales = 500.

Data type

The kind of value stored, such as str for text, int for whole numbers, float for decimals, and bool for True/False.

type()

Checks a value’s data type so an analyst can verify whether calculations or comparisons will work as intended.

Type conversion

Changes a value from one data type to another, such as int("21"), often needed because user input begins as text.

String

Text data enclosed in quotes, commonly used for labels, names, categories, and messages.

Truthiness

How Python treats values in conditions; empty strings are falsy, while nonempty strings are truthy.

List

An ordered, changeable collection of items used to store related values such as regions or product categories.

Zero-based indexing

Python counts list positions starting at 0, so regions[0] returns the first item.

len()

Returns the number of items in a list or rows in a DataFrame, helping measure the size of a collection or dataset.

.append()

Adds an item to the end of a list when new information must be included.

.insert()

Adds an item at a specified list position when order matters.

.pop()

Removes and returns an item, useful when an analyst needs to both delete and use a value.

.remove()

Deletes the first matching value from a list.

.sort()

Permanently sorts a list, changing the original order.

sorted()

Creates a sorted copy without changing the original list, useful when the original order still matters.

Sequence

Code that runs step by step in its written order.

Selection

Code that chooses among alternatives using conditions, usually through if, elif, and else.

Iteration

Repeating code through a for loop or while loop, often used to process many records or values.

Comparison operator

Compares values and produces a Boolean result, such as >, <, ==, or !=.

Membership operator in

Tests whether a value exists in a collection, such as checking whether a product is in a list of categories.

Logical operator and

Produces True only when both conditions are True, useful for filtering data with multiple requirements.

Logical operator or

Produces True when at least one condition is True, useful for keeping records that meet either condition.

Logical operator not

Reverses a Boolean condition, useful for excluding records that meet an unwanted condition.

if statement

Runs code only when a condition is True.

elif statement

Tests another condition after a previous if condition is False.

else statement

Runs a default action when none of the earlier conditions are True.

Indentation

Defines which statements belong inside a condition, loop, or function; incorrect indentation changes program logic.

Counter

A variable updated during a loop, such as count = count + 1, used to track repetitions or totals.

input()

Pauses the program and collects user input, which Python initially stores as a string.

while loop

Repeats code while its condition remains True; it requires an update so the loop can eventually end.

Infinite loop

A loop that never ends because its condition never becomes False, often caused by forgetting to update a counter.

for loop

Repeats once for each item in a collection or value in a range, making it useful for systematic processing.

range()

Creates a sequence of numbers used in loops; its start, stop, and step values determine how many iterations occur.

Function

A reusable named block of code that performs a specific task, reducing repetition and improving readability.

def

Keyword used to define a function before it can be called.

Function call

Runs a function by using its name followed by parentheses.

Parameter

A variable listed in a function definition that receives input when the function is called.

Argument

The actual value passed into a function when it is called.

Default parameter

A parameter with a preassigned value that is used when no argument is provided.

Local variable

A variable created inside a function that is generally available only within that function.

Pandas

A Python library for loading, organizing, inspecting, and analyzing tabular data.

DataFrame

A two-dimensional labeled data structure with rows and columns, similar to a spreadsheet or database table.

Series

A single DataFrame column, typically analyzed as one variable such as Profit or Region.

pd.read_excel()

Loads an Excel worksheet into a DataFrame so its data can be inspected and analyzed.

Unit of observation

What one row represents, such as one order, customer, or transaction; it determines how row-level results should be interpreted.

Unit of analysis

The level at which conclusions are made, such as by product, region, customer, or month.

Scope of data

The time period, population, sample, and business questions that the dataset can reasonably address.

Unique identifier

A column whose value uniquely identifies each row, helping detect duplicate records and distinguish observations.

Column schema

The set of column names, data types, and roles in a dataset, used to understand what each field represents.

Categorical column

A column containing labels or groups, such as Region or Category, commonly used to group data.

Numerical column

A column containing quantities, such as Sales, Profit, or Discount, commonly used in mathematical calculations.

Data quality

The accuracy, completeness, consistency, and plausibility of data, including missing values, errors, and outliers.

df.info()

Displays row and column counts, data types, and memory details so an analyst can assess dataset structure and spot missing values.

len(df)

Returns the number of DataFrame rows, helping an analyst understand dataset size or confirm a filter’s effect.

df.head()

Displays the first rows of a DataFrame to quickly check column contents, formatting, and whether data loaded correctly.

df.columns

Displays exact column names so code can reference fields correctly and analysts can identify the dataset schema.

df.describe()

Produces descriptive statistics for numerical columns, helping identify central values, spread, minimums, maximums, and potential outliers.

.unique()

Returns the distinct values in a column, helping an analyst inspect categories, detect typos, or find unexpected labels.

.value_counts()

Counts how often each distinct value occurs, helping identify common categories, rare categories, and possible data-quality issues.

Column selection

Choosing one or more DataFrame columns to focus analysis on variables relevant to a business question.

.loc[] filtering

Selects rows that meet a logical condition, allowing an analyst to isolate records such as a specific product subcategory.

Filter condition

A Boolean rule that decides which rows stay in an analysis, such as keeping only records where Sub-Category equals Tables.

groupby()

Splits data into categories and calculates results for each category, helping compare performance across regions, products, or customer segments.

Aggregation

A calculation that summarizes many records into one result, such as total profit, average sales, or order count.

.sum()

Adds numerical values, often used after grouping to find total sales or total profit by category.

.mean()

Calculates the average value, useful for comparing typical sales, profit, discounts, or performance across groups.

.agg()

Applies one or more aggregation functions to grouped data, allowing different columns to receive different summary calculations.

.sort_values()

Orders rows by a selected column, helping analysts rank the highest or lowest performing products, regions, or customers.

ascending=False

Sorts values from largest to smallest, useful for finding top performers or the largest losses first.

Pivot table

A cross-tabular summary that reshapes data to compare metrics across two dimensions, such as Region by Year.

pivot_table()

Builds a summary table with selected row groups, column groups, and aggregate values for multidimensional analysis.

Correlation

A measure from -1.0 to 1.0 describing the direction and strength of a linear relationship between two numerical variables.

.corr()

Calculates correlation between numerical columns, helping explore whether variables such as Discount and Profit tend to move together.

Correlation is not causation

A correlation can identify a relationship worth investigating but cannot prove that one variable causes the other.

pd.to_datetime()

Converts text values into date-time data so an analyst can correctly sort, filter, and analyze trends over time.

Issue validation

Checking whether an apparent problem is real before acting, such as confirming whether negative profit occurs repeatedly rather than in one unusual order.

Problem isolation

Using filters and grouped summaries to identify where an issue occurs, such as locating unprofitable categories, regions, or customer groups.

Root-cause exploration

Investigating factors linked to a problem after isolating it, such as examining whether discounts are associated with low profit.

Next analysis

The logical follow-up after an output; for example, after finding a low-profit category, group by region, customer segment, or discount level to locate the source of the issue.

Analytical purpose

The business reason for running code: inspect data, validate quality, summarize performance, compare groups, identify problems, or investigate possible drivers.

What is the key difference between using df.describe() and using df.groupby("Category")["Profit"].sum() when trying to understand business performance?

df.describe() gives a big-picture summary of all numerical data, such as averages, minimums, maximums, and spread. Use it first to understand the dataset and look for unusual values.midterm_exam_study_guide.docx

df.groupby("Category")["Profit"].sum() gives a category-by-category profit total. Use it to compare categories and find which ones make the most profit or cause losses.