Revert "fix: Address content-policy issues behind AdSense low-value verdict"

This reverts commit 4b7ff22.

Author: singhsidhukuldeep

docs/Cheat-Sheets/Hypothesis-Tests.md

@@ -15,7 +15,7 @@ A [**statistical hypothesis test**](https://en.wikipedia.org/wiki/Statistical_h
 
 **Few Notes:**
 
-- Most tests tolerate mild violations of their assumptions (expected distribution, sample size, and so on): the reliability of the result erodes gradually as an assumption is stretched, instead of the test suddenly producing nonsense.
+- When it comes to assumptions such as the expected distribution of data or sample size, the results of a given test are likely to degrade gracefully rather than become immediately unusable if an assumption is violated.
 - Generally, data samples need to be representative of the domain and large enough to expose their distribution to analysis.
 - In some cases, the data can be corrected to meet the assumptions, such as correcting a nearly normal distribution to be normal by removing outliers, or using a correction to the degrees of freedom in a statistical test when samples have differing variance, to name two examples.
 

docs/Cheat-Sheets/SQL.md

@@ -9,43 +9,29 @@ description: A comprehensive reference guide for SQL, covering data types, DDL,
 
 This cheat sheet provides an exhaustive overview of SQL (Structured Query Language), covering data types, Data Definition Language (DDL), Data Manipulation Language (DML), Data Query Language (DQL), Transaction Control Language (TCL), joins, subqueries, window functions, common table expressions (CTEs), and best practices. It aims to be a complete reference for writing and understanding SQL queries.  This cheat sheet is designed to be generally applicable across different SQL database systems (e.g., MySQL, PostgreSQL, SQL Server, Oracle, SQLite), but notes specific differences where significant.
 
-??? tip "SQL at a Glance"
-    **Command categories:**
-
-    | Category | Purpose | Key statements |
-    |----------|---------|----------------|
-    | DQL | Read data | `SELECT` |
-    | DML | Change data | `INSERT`, `UPDATE`, `DELETE` |
-    | DDL | Change structure | `CREATE`, `ALTER`, `DROP`, `TRUNCATE` |
-    | DCL | Permissions | `GRANT`, `REVOKE` |
-    | TCL | Transactions | `BEGIN`, `COMMIT`, `ROLLBACK`, `SAVEPOINT` |
-
-    **Query skeleton (written order vs. logical execution order):**
-
-    | Written order | Executed order |
-    |---------------|----------------|
-    | `SELECT` | 5th |
-    | `FROM` / `JOIN` | 1st |
-    | `WHERE` | 2nd |
-    | `GROUP BY` | 3rd |
-    | `HAVING` | 4th |
-    | `ORDER BY` | 6th |
-    | `LIMIT` / `OFFSET` | 7th |
-
-    This is why a column alias defined in `SELECT` cannot be referenced in `WHERE`, but usually can in `ORDER BY`.
-
-    **Join types in one line each:**
-
-    | Join | Returns |
-    |------|---------|
-    | `INNER JOIN` | Only rows with a match in both tables |
-    | `LEFT JOIN` | All left rows, matched right rows or NULLs |
-    | `RIGHT JOIN` | All right rows, matched left rows or NULLs |
-    | `FULL OUTER JOIN` | All rows from both sides, NULLs where unmatched |
-    | `CROSS JOIN` | Every combination (Cartesian product) |
-    | `SELF JOIN` | A table joined to itself via aliases |
-
-    **Filter fast-picks:** `BETWEEN a AND b` (inclusive), `IN (...)`, `LIKE 'A%'` (prefix match), `IS NULL` (never `= NULL`), `EXISTS (subquery)` for correlated checks.
+??? tip "SQL Cheat Sheet Images"
+    <figure markdown="span">
+        ![SQL cheat sheet page 1](https://www.sqltutorial.org/wp-content/uploads/2016/04/SQL-Cheet-Sheet-1.png){ width="100%" }
+        ![SQL cheat sheet page 2](https://www.sqltutorial.org/wp-content/uploads/2016/04/SQL-Cheat-Sheet-2.png){ width="100%" }
+        ![SQL cheat sheet page 3](https://www.sqltutorial.org/wp-content/uploads/2016/04/SQL-Cheat-Sheet-3.png){ width="100%" }
+        <figcaption>https://www.sqltutorial.org/sql-cheat-sheet/</figcaption>
+    </figure>
+    ---
+    <figure markdown="span">
+        ![MySQL cheat sheet page 1](https://learnsql.com/blog/mysql-cheat-sheet/mysql-cheat-sheet-a4-page-1.webp){ width="100%" }
+        ![MySQL cheat sheet page 2](https://learnsql.com/blog/mysql-cheat-sheet/mysql-cheat-sheet-a4-page-2.webp){ width="100%" }
+        <figcaption>https://learnsql.com/blog/mysql-cheat-sheet/</figcaption>
+    </figure>
+    ---
+    <figure markdown="span">
+        ![SQL for Data Science cheat sheet](https://media.datacamp.com/legacy/image/upload/v1714038485/SQL_for_Data_Science_826c347c43.png){ width="100%" }
+        <figcaption>https://www.datacamp.com/cheat-sheet/sql-basics-cheat-sheet</figcaption>
+    </figure>
+    ---
+    <figure markdown="span">
+        ![MySQL cheat sheet](https://media.datacamp.com/legacy/image/upload/v1698139537/My_SQL_Cheat_Sheet_f2d0d7da20.png){ width="100%" }
+        <figcaption>https://www.datacamp.com/cheat-sheet/my-sql-basics-cheat-sheet</figcaption>
+    </figure>
 
 
 ## Data Types

docs/Interview-Questions/AB-testing.md

@@ -7542,7 +7542,7 @@ This document provides a curated list of A/B Testing and Experimentation intervi
 
 ??? success "View Answer"
 
-    **Regression Adjustment** (also called **CUPED** - Controlled-experiment Using Pre-Experiment Data) uses **pre-experiment covariates** to reduce variance in treatment effect estimates by **40-70%**, enabling faster experiments and smaller sample sizes. It's one of the **most powerful variance reduction techniques** used in large-scale industry experimentation.
+    **Regression Adjustment** (also called **CUPED** - Controlled-experiment Using Pre-Experiment Data) uses **pre-experiment covariates** to reduce variance in treatment effect estimates by **40-70%**, enabling faster experiments and smaller sample sizes. It's the **most powerful variance reduction technique** used by Google, Meta, Netflix, and Uber.
 
     **Core Idea:**
 

docs/Interview-Questions/Interview-Question-Resources.md

@@ -1,5 +1,4 @@
 ---
-robots: noindex, follow
 title: Data Science Interview Question Resources
 description: Community-curated collection of the best sources for data science interview questions - GitHub repositories, practice platforms, and real interview experiences
 ---

docs/Interview-Questions/Interview-Questions.md

@@ -1,5 +1,4 @@
 ---
-robots: noindex, follow
 title: Data Science Interview Questions - Complete Collection
 description: Comprehensive collection of 1000+ data science interview questions covering ML, Python, SQL, NLP, statistics, and system design asked at Google, Meta, Amazon, and top tech companies.
 # hide:

docs/Interview-Questions/Machine-Learning.md

@@ -95,6 +95,9 @@ Master these frequently asked ML questions with detailed explanations, code exam
     class BiasVarianceAnalyzer:
         """
         Production-quality analyzer for bias-variance tradeoff.
+        
+        Used by Google's AutoML team to diagnose model selection issues
+        and by Netflix to optimize recommendation model complexity.
         """
 
         def __init__(self, n_bootstrap: int = 30):
@@ -177,7 +180,7 @@ Master these frequently asked ML questions with detailed explanations, code exam
             """
             Estimate bias and variance using bootstrap sampling.
 
-            This technique is widely used in production ML platforms to
+            This is the technique used by Meta's ML platform to
             diagnose model performance issues at scale.
             """
             predictions = np.zeros((self.n_bootstrap, len(X_test)))
@@ -1201,7 +1204,7 @@ Master these frequently asked ML questions with detailed explanations, code exam
     │  4. COSINE ANNEALING:                                          │
     │     η ─────╲    ╱─────╲                                      │
     │            ╲__╱       ╲__╱                                   │
-    │     Smooth cycles                                             │
+    │     Smooth cycles (used by OpenAI)                            │
     │                                                                │
     │  5. WARMUP + DECAY:                                            │
     │     η      ╱‾‾╲                                               │
@@ -1488,7 +1491,7 @@ Master these frequently asked ML questions with detailed explanations, code exam
             """
             Nested cross-validation for unbiased hyperparameter tuning.
 
-            This is a widely used standard for model selection.
+            This is the gold standard used by Google for model selection.
             Outer loop estimates generalization error.
             Inner loop selects best hyperparameters.
             """

docs/Interview-Questions/Probability.md

@@ -285,6 +285,9 @@ This document provides a curated list of common probability interview questions
     class ConditionalProbabilityAnalyzer:
         """
         Production-ready analyzer for conditional probability and independence.
+        
+        Used by Netflix for user behavior analysis, Google for ad targeting,
+        and Meta for feed ranking independence tests.
         """
 
         def __init__(self, tolerance: float = 1e-6):
@@ -390,6 +393,8 @@ This document provides a curated list of common probability interview questions
         ) -> Dict[str, float]:
             """
             Perform chi-square test for independence.
+            
+            Used by Google Analytics for feature correlation analysis.
             """
             from scipy.stats import chi2_contingency
 

docs/Interview-Questions/Scikit-Learn.md

@@ -5668,6 +5668,7 @@ This is updated frequently but right now this is the most exhaustive list of typ
         Production-grade ML model debugger
 
         Systematically diagnoses model failures using a checklist approach.
+        Used by Google, Meta, Amazon ML teams for production debugging.
 
         Time Complexity: O(n × d + model_training_time)
         Space: O(n × d) for storing data

docs/Interview-Questions/data-structures-algorithms.md

@@ -78,6 +78,7 @@ This is updated frequently but right now this is the most exhaustive list of typ
     class TwoSumSolver:
         """
         Production-quality Two Sum solver with multiple strategies.
+        Used by Google for pair matching in distributed systems.
         """
 
         def __init__(self, strategy: TwoSumStrategy = TwoSumStrategy.HASH_MAP):
@@ -356,6 +357,7 @@ This is updated frequently but right now this is the most exhaustive list of typ
     class LinkedListReverser:
         """
         Production linked list reversal with multiple approaches.
+        Used by Amazon for order processing queue reversal.
         """
 
         def __init__(self):
@@ -663,6 +665,7 @@ This is updated frequently but right now this is the most exhaustive list of typ
     class ParenthesesValidator:
         """
         Production bracket validation system.
+        Used by Google's code parsers and Amazon's JSON validators.
         """
 
         def __init__(self, allow_angle_brackets: bool = False):
@@ -984,6 +987,7 @@ This is updated frequently but right now this is the most exhaustive list of typ
     class BinarySearchEngine:
         """
         Production binary search with all variants.
+        Used by Google for searching 100B+ sorted documents.
         """
 
         def __init__(self):
@@ -1354,6 +1358,7 @@ This is updated frequently but right now this is the most exhaustive list of typ
     class MaximumSubarrayFinder:
         """
         Production maximum subarray solver with multiple strategies.
+        Used by Netflix for viewing pattern analysis.
         """
 
         def __init__(self):
@@ -2135,6 +2140,7 @@ This is updated frequently but right now this is the most exhaustive list of typ
     class SlidingWindowSolver:
         """
         Production sliding window implementation.
+        Used by Uber for passenger matching optimization.
         """
 
         def __init__(self):

docs/Online-Material/Online-Material-for-Learning.md

@@ -1,5 +1,4 @@
 ---
-robots: noindex, follow
 title: Online Study Material
 description: Ultra-comprehensive collection of online resources, courses, tutorials, learning platforms, and career development materials for data science, machine learning, AI, and related fields.
 comments: true