addweb-solution commited on
Commit
9becf0f
·
verified ·
1 Parent(s): e435ddf

Upload DATA_FORMAT.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. DATA_FORMAT.md +34 -0
DATA_FORMAT.md CHANGED
@@ -52,6 +52,26 @@ Prediction quality is better if your history CSV also includes:
52
  - `away_tactic_id`
53
  - `home_coach_id`
54
  - `away_coach_id`
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
  These optional fields help the wrapper compute richer features with fewer fallbacks.
57
 
@@ -65,7 +85,9 @@ match_id,date,home_team,away_team,home_goals,away_goals,home_team_id,away_team_i
65
  The bundled synthetic history currently includes:
66
  - `120` rows
67
  - `20` La Liga team names
 
68
  - enough depth for rolling-form demo calculations
 
69
 
70
  ## Fixture CSV Requirements
71
  For `predict_batch.py`, the fixtures CSV should contain:
@@ -115,6 +137,18 @@ If you keep using only the synthetic sample files:
115
  - the methods will behave correctly
116
  - but the predictions should be treated as demonstration-quality, not production-quality
117
 
 
 
 
 
 
 
 
 
 
 
 
 
118
  ## What Not To Publish
119
  Do not publish large internal historical CSVs unless redistribution rights are explicit.
120
 
 
52
  - `away_tactic_id`
53
  - `home_coach_id`
54
  - `away_coach_id`
55
+ - `home_player_minutes_total_prev5`
56
+ - `away_player_minutes_total_prev5`
57
+ - `home_player_goals_total_prev5`
58
+ - `away_player_goals_total_prev5`
59
+ - `home_player_assists_total_prev5`
60
+ - `away_player_assists_total_prev5`
61
+ - `home_player_yellow_cards_total_prev5`
62
+ - `away_player_yellow_cards_total_prev5`
63
+ - `home_player_red_cards_total_prev5`
64
+ - `away_player_red_cards_total_prev5`
65
+ - `home_player_starters_count_prev5`
66
+ - `away_player_starters_count_prev5`
67
+ - `home_player_used_count_prev5`
68
+ - `away_player_used_count_prev5`
69
+ - `home_player_injured_count_prev5`
70
+ - `away_player_injured_count_prev5`
71
+ - `home_player_suspended_count_prev5`
72
+ - `away_player_suspended_count_prev5`
73
+ - `home_tactic_stability_last5`
74
+ - `away_tactic_stability_last5`
75
 
76
  These optional fields help the wrapper compute richer features with fewer fallbacks.
77
 
 
85
  The bundled synthetic history currently includes:
86
  - `120` rows
87
  - `20` La Liga team names
88
+ - `35` columns
89
  - enough depth for rolling-form demo calculations
90
+ - richer optional context columns for better demonstration quality
91
 
92
  ## Fixture CSV Requirements
93
  For `predict_batch.py`, the fixtures CSV should contain:
 
137
  - the methods will behave correctly
138
  - but the predictions should be treated as demonstration-quality, not production-quality
139
 
140
+ ## Why The Model Can Use 48 Signals Even If The CSV Has Fewer Columns
141
+ The trained model expects `48` numeric input signals at inference time.
142
+
143
+ Those signals are produced in three ways:
144
+ 1. directly from columns already present in the history CSV
145
+ 2. derived by the wrapper from past match rows
146
+ 3. filled by fallback defaults when richer optional context is missing
147
+
148
+ So the public rule is:
149
+ - the CSV does not need to contain all `48` final model inputs as raw columns
150
+ - but a richer CSV allows the wrapper to produce a stronger feature row
151
+
152
  ## What Not To Publish
153
  Do not publish large internal historical CSVs unless redistribution rights are explicit.
154