05/23 Phase 4

core/analyzer.py

@@ -0,0 +1,127 @@
+"""
+core/analyzer.py
+----------------
+All statistical analysis functions for LottoSight.
+Each function takes game_id and returns structured Python data
+(dicts / lists) — no UI concerns here.
+"""
+
+from collections import Counter
+from itertools import combinations
+
+from db.models import get_all_draws_numbers, get_game_by_id
+
+
+def frequency_analysis(game_id, last_n=None):
+    """
+    Count appearances of each main ball.
+    last_n: restrict to the most recent N draws (None = all).
+    Returns {number: count} sorted high → low.
+    """
+    draws = get_all_draws_numbers(game_id)   # ASC order
+    if last_n and last_n > 0:
+        draws = draws[-last_n:]
+
+    counter = Counter()
+    for draw in draws:
+        counter.update(draw["numbers"])
+
+    return dict(sorted(counter.items(), key=lambda kv: kv[1], reverse=True))
+
+
+def gap_analysis(game_id):
+    """
+    Draws elapsed since each number last appeared.
+    gap=0  → appeared in the most recent draw.
+    gap=N  → last appeared N draws before the current one.
+    Numbers never drawn receive gap = total draw count.
+    Returns {number: gap} for every number in the pool.
+    """
+    draws = get_all_draws_numbers(game_id)   # ASC order
+    if not draws:
+        return {}
+
+    game  = get_game_by_id(game_id)
+    total = len(draws)
+
+    last_seen = {}
+    for idx, draw in enumerate(draws):
+        for n in draw["numbers"]:
+            last_seen[n] = idx   # keep updating → final value = most recent draw index
+
+    result = {}
+    for n in range(1, game["main_max"] + 1):
+        if n in last_seen:
+            result[n] = (total - 1) - last_seen[n]
+        else:
+            result[n] = total
+
+    return result
+
+
+def positional_frequency(game_id):
+    """
+    How often each number appears at each draw position (1-indexed).
+    Returns {pos: {number: count}} for positions 1 .. main_count.
+    """
+    draws = get_all_draws_numbers(game_id)
+    game  = get_game_by_id(game_id)
+    main_count = game["main_count"]
+
+    result = {pos: Counter() for pos in range(1, main_count + 1)}
+    for draw in draws:
+        for pos, num in enumerate(draw["numbers"][:main_count], start=1):
+            result[pos][num] += 1
+
+    return {pos: dict(c) for pos, c in result.items()}
+
+
+def pair_analysis(game_id, top_n=50):
+    """
+    Most frequent pairs of numbers appearing together in the same draw.
+    Returns {(n1, n2): count} for the top_n pairs (n1 < n2), high → low.
+    """
+    draws = get_all_draws_numbers(game_id)
+    counter = Counter()
+    for draw in draws:
+        for pair in combinations(sorted(draw["numbers"]), 2):
+            counter[pair] += 1
+
+    return dict(counter.most_common(top_n))
+
+
+def odd_even_ratio(game_id):
+    """
+    Odd vs even ball count per draw.
+    Returns [{"date": str, "odd": int, "even": int}, ...] in chronological order.
+    """
+    draws = get_all_draws_numbers(game_id)
+    result = []
+    for draw in draws:
+        odd  = sum(1 for n in draw["numbers"] if n % 2 != 0)
+        even = len(draw["numbers"]) - odd
+        result.append({"date": draw["draw_date"], "odd": odd, "even": even})
+    return result
+
+
+def sum_range_analysis(game_id):
+    """
+    Sum of main balls per draw.
+    Returns [{"date": str, "sum": int}, ...] in chronological order.
+    """
+    draws = get_all_draws_numbers(game_id)
+    return [{"date": d["draw_date"], "sum": sum(d["numbers"])} for d in draws]
+
+
+def delta_analysis(game_id):
+    """
+    Differences between consecutive sorted numbers within each draw.
+    Returns [{"date": str, "deltas": [int, ...]}, ...] in chronological order.
+    """
+    draws = get_all_draws_numbers(game_id)
+    result = []
+    for draw in draws:
+        s      = sorted(draw["numbers"])
+        deltas = [s[i + 1] - s[i] for i in range(len(s) - 1)]
+        result.append({"date": draw["draw_date"], "deltas": deltas})
+    return result