|
| 1 | +# Problem 3482: Analyze Organization Hierarchy |
| 2 | +# Difficulty: Hard |
| 3 | + |
| 4 | +# Table: Employees |
| 5 | +# +----------------+---------+ |
| 6 | +# | Column Name | Type | |
| 7 | +# +----------------+---------+ |
| 8 | +# | employee_id | int | |
| 9 | +# | employee_name | varchar | |
| 10 | +# | manager_id | int | |
| 11 | +# | salary | int | |
| 12 | +# | department | varchar | |
| 13 | +# +----------------+----------+ |
| 14 | +# employee_id is the unique key for this table. |
| 15 | +# Each row contains information about an employee, including their ID, name, their manager's ID, salary, and department. |
| 16 | +# manager_id is null for the top-level manager (CEO). |
| 17 | + |
| 18 | +# Problem Statement: |
| 19 | +# Write a solution to analyze the organizational hierarchy and answer the following: |
| 20 | +# - Hierarchy Levels: For each employee, determine their level in the organization (CEO is level 1, employees reporting directly to the CEO are level 2, and so on). |
| 21 | +# - Team Size: For each employee who is a manager, count the total number of employees under them (direct and indirect reports). |
| 22 | +# - Salary Budget: For each manager, calculate the total salary budget they control (sum of salaries of all employees under them, including indirect reports, plus their own salary). |
| 23 | +# Return the result table ordered by the result ordered by level in ascending order, then by budget in descending order, and finally by employee_name in ascending order. |
| 24 | + |
| 25 | +# Solution |
| 26 | + |
| 27 | +import pandas as pd |
| 28 | +from collections import defaultdict |
| 29 | + |
| 30 | +def analyze_organization_hierarchy(df: pd.DataFrame) -> pd.DataFrame: |
| 31 | + |
| 32 | + def traverseGraph(mgr: int, lev: int) -> None: |
| 33 | + # I set the current manager's level |
| 34 | + levl[mgr] = lev |
| 35 | + |
| 36 | + # I traverse through each employee reporting to this manager |
| 37 | + for emp in grph[mgr]: |
| 38 | + traverseGraph(emp, lev + 1) |
| 39 | + |
| 40 | + # I accumulate team size and budget recursively |
| 41 | + team[mgr] += team[emp] + 1 |
| 42 | + bdgt[mgr] += bdgt[emp] |
| 43 | + return |
| 44 | + |
| 45 | + # I build the manager-to-employee graph |
| 46 | + grph = defaultdict(list) |
| 47 | + levl, team, bdgt = defaultdict(int), defaultdict(int), defaultdict(int) |
| 48 | + |
| 49 | + # I identify the top-level manager (CEO) |
| 50 | + boss = df.loc[df.manager_id.isna(), "employee_id"].values[0] |
| 51 | + |
| 52 | + # I populate the graph and initialize budgets with individual salaries |
| 53 | + for mgr, emp, sal in zip(df.manager_id, df.employee_id, df.salary): |
| 54 | + grph[mgr].append(emp) |
| 55 | + bdgt[emp] = sal |
| 56 | + |
| 57 | + # I start DFS from the CEO to populate level, team size, and budget |
| 58 | + traverseGraph(boss, 1) |
| 59 | + |
| 60 | + # I add the computed columns to the DataFrame |
| 61 | + df['level'] = df.employee_id.apply(lambda x: levl[x]) |
| 62 | + df['team_size'] = df.employee_id.apply(lambda x: team[x]) |
| 63 | + df['budget'] = df.employee_id.apply(lambda x: bdgt[x]) |
| 64 | + |
| 65 | + # I return the final sorted result as per requirements |
| 66 | + return df.sort_values(['level','budget','employee_name'], |
| 67 | + ascending=[1,0,1])[['employee_id', 'employee_name', 'level', 'team_size', 'budget']] |
| 68 | + |
| 69 | +# Intuition: |
| 70 | +# I need to compute hierarchical information in an organization using a tree-like structure. |
| 71 | +# Each manager has direct reports who may themselves be managers, so I use DFS to calculate: |
| 72 | +# - level (distance from CEO) |
| 73 | +# - team size (number of all employees under a manager) |
| 74 | +# - budget (sum of salaries under the manager's control) |
| 75 | + |
| 76 | +# Explanation: |
| 77 | +# I create a graph where each manager points to a list of their direct reports. |
| 78 | +# I initialize the `budget` dictionary with employees' own salaries and fill in team size and levels via DFS traversal. |
| 79 | +# While returning from recursion, I aggregate the budget and team size upward through the tree. |
| 80 | +# The final DataFrame gets three new columns: `level`, `team_size`, and `budget`. |
| 81 | +# I sort the DataFrame as required by level (asc), budget (desc), and employee_name (asc), and return the required columns. |
0 commit comments