Update app.py

app.py

@@ -1,197 +1,67 @@
-import os, io, re, math
-import pandas as pd
-import numpy as np
-import gradio as gr
-import pycountry
-
-# === CONFIG ===
-DATA_FILE = "players.dataset.xlsx"
-BASE_POSITIONS = ["CB","RB","LB","CDM","CM","CAM","RW","ST","LW"]
-
-EXCLUDED_NATIONS = {
-    "PALESTINE","STATE OF PALESTINE","PALESTINIAN TERRITORY","PALESTINIAN TERRITORIES","PSE","PS"
-}
-
-CANON = {
-    "name": ["name","player","player_name"],
-    "age": ["age"],
-    "position": ["position","pos"],
-    "nation": ["nation","nationality","country","citizenship"],
-    "club": ["club","team","current_club"],
-    "overall": ["overall","rating","ovr"],
-    "potential": ["potential","pot"],
-    "value": ["value","value_eur","market_value","market_value_eur"],
-    "wage": ["wage","wage_eur","salary","salary_eur"],
-    "height_cm": ["height","height_cm","cm_height"],
-    "weight_kg": ["weight","weight_kg","kg_weight"],
-}
-
-def _canon_map(columns):
-    cols = [str(c).strip() for c in columns]
-    lower = [c.lower().strip() for c in cols]
-    out = {}
-    for std, variants in CANON.items():
-        for v in variants:
-            if v in lower:
-                out[std] = cols[lower.index(v)]
-                break
-    return out
-
-def _to_number(x):
-    if pd.isna(x): return np.nan
-    s = re.sub(r"[^\d.\-]", "", str(x))
-    try: return float(s)
-    except: return np.nan
-
-def _to_full_country(n):
-    if pd.isna(n): return None
-    s = str(n).strip()
-    candidate = None
-    if len(s) <= 3:
-        c = pycountry.countries.get(alpha_3=s.upper())
-        if c: candidate = c.name
-        if candidate is None:
-            c = pycountry.countries.get(alpha_2=s.upper())
-            if c: candidate = c.name
-    if candidate is None:
-        candidate = s
-    norm = re.sub(r"\s+"," ", candidate).strip().upper()
-    if norm in EXCLUDED_NATIONS:
-        return None
-    return candidate
-
-def load_df():
-    if not os.path.exists(DATA_FILE):
-        return pd.DataFrame(columns=[
-            "Name","Age","Position","Nation","Club","Overall","Potential",
-            "Height_cm","Weight_kg","Value","Wage"
-        ])
-    df = pd.read_excel(DATA_FILE, engine="openpyxl")
-    df.columns = [str(c).strip() for c in df.columns]
-    cmap = _canon_map(df.columns)
-
-    out = pd.DataFrame()
-    out["Name"]       = df.get(cmap.get("name"), pd.Series(dtype=str)).astype(str).str.strip()
-    out["Age"]        = df.get(cmap.get("age"), pd.Series(dtype=object)).apply(_to_number)
-    out["Position"]   = df.get(cmap.get("position"), pd.Series(dtype=str)).astype(str).str.upper().str.strip()
-    nat_raw           = df.get(cmap.get("nation"), pd.Series(dtype=str))
-    out["Nation"]     = nat_raw.apply(_to_full_country) if nat_raw is not None else pd.Series(dtype=str)
-
-    club = df.get(cmap.get("club"), pd.Series(dtype=str)).astype(str).str.strip()
-    club = club.replace({"": pd.NA, "nan": pd.NA, "None": pd.NA})
-    out["Club"]       = club
-
-    out["Overall"]    = df.get(cmap.get("overall"), pd.Series(dtype=object)).apply(_to_number)
-    out["Potential"]  = df.get(cmap.get("potential"), pd.Series(dtype=object)).apply(_to_number)
-    out["Value"]      = df.get(cmap.get("value"), pd.Series(dtype=object)).apply(_to_number)
-    out["Wage"]       = df.get(cmap.get("wage"), pd.Series(dtype=object)).apply(_to_number)
-    out["Height_cm"]  = df.get(cmap.get("height_cm"), pd.Series(dtype=object)).apply(_to_number)
-    out["Weight_kg"]  = df.get(cmap.get("weight_kg"), pd.Series(dtype=object)).apply(_to_number)
-
-    out = out[~out["Nation"].isna()].reset_index(drop=True)
-    return out
-
-DF = load_df()
-
-def positions_list():
-    vals = set(BASE_POSITIONS)
-    if "Position" in DF.columns:
-        vals |= set(str(x).upper().strip() for x in DF["Position"].dropna().unique())
-    return sorted(vals)
-
-def nations_list():
-    # Always list all countries (minus exclusions), not just those in the dataset
-    all_names = []
-    for c in pycountry.countries:
-        nm = c.name
-        if re.sub(r"\s+"," ", nm).upper() not in EXCLUDED_NATIONS:
-            all_names.append(nm)
-    return sorted(set(all_names))
-
-def clubs_list():
-    if "Club" not in DF.columns: return []
-    vals = [c for c in DF["Club"].dropna().unique().tolist() if str(c).strip()]
-    return sorted(set(vals))
-
-def filter_players(positions, nations, clubs, min_overall, min_potential,
-                   max_age, min_h, max_h, min_w, max_w, max_val, max_wage, query):
-    df = DF.copy()
-    if positions:   df = df[df["Position"].isin(positions)]
-    if nations:     df = df[df["Nation"].isin(nations)]
-    if clubs:       df = df[df["Club"].isin(clubs)]
-    if not math.isnan(min_overall):   df = df[df["Overall"]   >= min_overall]
-    if not math.isnan(min_potential): df = df[df["Potential"] >= min_potential]
-    if not math.isnan(max_age):       df = df[df["Age"]       <= max_age]
-    if not math.isnan(min_h):         df = df[df["Height_cm"] >= min_h]
-    if not math.isnan(max_h):         df = df[df["Height_cm"] <= max_h]
-    if not math.isnan(min_w):         df = df[df["Weight_kg"] >= min_w]
-    if not math.isnan(max_w):         df = df[df["Weight_kg"] <= max_w]
-    if not math.isnan(max_val):       df = df[df["Value"]     <= max_val]
-    if not math.isnan(max_wage):      df = df[df["Wage"]      <= max_wage]
-    if query:
-        q = query.strip().lower()
-        df = df[df.apply(lambda r: any(
-            q in str(r.get(c, "")).lower()
-            for c in ["Name","Club","Position","Nation"]
-        ), axis=1)]
-    cols = [c for c in ["Name","Age","Position","Nation","Club","Overall","Potential",
-                        "Height_cm","Weight_kg","Value","Wage"] if c in df.columns]
-    return df[cols].reset_index(drop=True)
-
-def to_csv_bytes(df):
-    buf = io.StringIO()
-    df.to_csv(buf, index=False, encoding="utf-8")
-    return buf.getvalue().encode("utf-8")
-
 # === UI ===
 THEME = gr.themes.Soft(primary_hue="blue")
 CSS = """
 #title { text-align:center; }
-.card { border-radius:16px; padding:14px; background:#fff; }
+.bubble { background:#fff; border-radius:16px; padding:12px; box-shadow:0 2px 10px rgba(0,0,0,.06); }
+.grid { gap:12px; }
 .stat { font-weight:600; font-size:14px; }
 """
 
 with gr.Blocks(theme=THEME, css=CSS) as demo:
     gr.Markdown("<h1 id='title'>ProScout — Player Finder</h1>")
 
-    # Filters in three columns, results wide on the right
+    # Filters area: 3 columns, EACH control in its own "bubble"
     with gr.Row():
-        # Column 1: positions + nations/clubs + free-text search at the end
-        with gr.Column(scale=1, elem_classes="card"):
-            pos = gr.CheckboxGroup(positions_list(), label="Positions", value=[], info="Pick one or more")
-            nat = gr.Dropdown(nations_list(), multiselect=True, label="Nations", value=[], filterable=True)
-            clu = gr.Dropdown(clubs_list(), multiselect=True, label="Clubs", value=[], filterable=True)
-            query = gr.Textbox(label="Search", placeholder="e.g., Maccabi, Brazil, CAM")
-
-        # Column 2: ratings & age
-        with gr.Column(scale=1, elem_classes="card"):
-            min_ovr = gr.Slider(0, 99, value=0, step=1, label="Min Overall")
-            min_pot = gr.Slider(0, 99, value=0, step=1, label="Min Potential")
-            max_age = gr.Slider(15, 45, value=45, step=1, label="Max Age")
-
-        # Column 3: physical & financial
-        with gr.Column(scale=1, elem_classes="card"):
-            min_h = gr.Slider(140, 210, value=140, step=1, label="Min Height (cm)")
-            max_h = gr.Slider(140, 210, value=210, step=1, label="Max Height (cm)")
-            min_w = gr.Slider(45, 120, value=45, step=1, label="Min Weight (kg)")
-            max_w = gr.Slider(45, 120, value=120, step=1, label="Max Weight (kg)")
-            max_val = gr.Number(value=np.nan, label="Max Value (EUR)")
-            max_wage = gr.Number(value=np.nan, label="Max Wage (EUR)")
-
-        # Results panel (wide)
-        with gr.Column(scale=2, elem_classes="card"):
-            results = gr.Dataframe(row_count=(12,"dynamic"), wrap=True, interactive=False, label="Results")
-            with gr.Row():
-                count_box = gr.Markdown("", elem_classes="stat")
-                avg_ovr_box = gr.Markdown("", elem_classes="stat")
-                avg_age_box = gr.Markdown("", elem_classes="stat")
-            dl = gr.DownloadButton("Download CSV")
-
-    # Button full-width under filters/results
+        # Column 1
+        with gr.Column(scale=1, elem_classes="grid"):
+            with gr.Group(elem_classes="bubble"):
+                pos = gr.CheckboxGroup(positions_list(), label="Positions", value=[], info="Pick one or more")
+            with gr.Group(elem_classes="bubble"):
+                nat = gr.Dropdown(nations_list(), multiselect=True, label="Nations", value=[], filterable=True)
+            with gr.Group(elem_classes="bubble"):
+                clu = gr.Dropdown(clubs_list(), multiselect=True, label="Clubs", value=[], filterable=True)
+            with gr.Group(elem_classes="bubble"):
+                query = gr.Textbox(label="Search", placeholder="e.g., Maccabi, Brazil, CAM")
+
+        # Column 2
+        with gr.Column(scale=1, elem_classes="grid"):
+            with gr.Group(elem_classes="bubble"):
+                min_ovr = gr.Slider(0, 99, value=0, step=1, label="Min Overall")
+            with gr.Group(elem_classes="bubble"):
+                min_pot = gr.Slider(0, 99, value=0, step=1, label="Min Potential")
+            with gr.Group(elem_classes="bubble"):
+                max_age = gr.Slider(15, 45, value=45, step=1, label="Max Age")
+
+        # Column 3
+        with gr.Column(scale=1, elem_classes="grid"):
+            with gr.Group(elem_classes="bubble"):
+                min_h = gr.Slider(140, 210, value=140, step=1, label="Min Height (cm)")
+            with gr.Group(elem_classes="bubble"):
+                max_h = gr.Slider(140, 210, value=210, step=1, label="Max Height (cm)")
+            with gr.Group(elem_classes="bubble"):
+                min_w = gr.Slider(45, 120, value=45, step=1, label="Min Weight (kg)")
+            with gr.Group(elem_classes="bubble"):
+                max_w = gr.Slider(45, 120, value=120, step=1, label="Max Weight (kg)")
+            with gr.Group(elem_classes="bubble"):
+                max_val = gr.Number(value=np.nan, label="Max Value (EUR)")
+            with gr.Group(elem_classes="bubble"):
+                max_wage = gr.Number(value=np.nan, label="Max Wage (EUR)")
+
+        # Results panel (wide, also a bubble)
+        with gr.Column(scale=2):
+            with gr.Group(elem_classes="bubble"):
+                results = gr.Dataframe(row_count=(12,"dynamic"), wrap=True, interactive=False, label="Results")
+                with gr.Row():
+                    count_box = gr.Markdown("", elem_classes="stat")
+                    avg_ovr_box = gr.Markdown("", elem_classes="stat")
+                    avg_age_box = gr.Markdown("", elem_classes="stat")
+                dl = gr.DownloadButton("Download CSV")
+
+    # Full-width Search button in its own bubble below filters
     with gr.Row():
-        gr.Markdown("")  # left spacer
-        btn = gr.Button("Search", variant="primary")
-        gr.Markdown("")  # right spacer
+        with gr.Column(scale=3):
+            with gr.Group(elem_classes="bubble"):
+                btn = gr.Button("Search")
 
     def _run(positions, nations, clubs, min_overall, min_potential,
              max_age, min_h, max_h, min_w, max_w, max_val, max_wage, query):
@@ -203,7 +73,6 @@ with gr.Blocks(theme=THEME, css=CSS) as demo:
         csv_bytes = to_csv_bytes(df)
         return df, f"**Players:** {count}", f"**Avg OVR:** {avg_ovr}", f"**Avg Age:** {avg_age}", csv_bytes
 
-    # Load initial data automatically
     demo.load(
         _run,
         inputs=[pos,nat,clu,min_ovr,min_pot,max_age,min_h,max_h,min_w,max_w,max_val,max_wage,query],