Remove more unecessary files. Restore Data Preprocess

3_Demo.ipynb

@@ -23,18 +23,18 @@
    "source": [
     "path = Path()\n",
     "df = pd.read_csv(\"rookie_year.csv\")\n",
-    "learn = load_learner(path/\"export.pkl\")"
+    "learn = load_learner(path/\"export.pkl\")\n",
+    "columns = [\"Name\", \"G\", \"GS\", \"Cmp\", \"Att\", \"Yds\", \"Cmp%\", \"TD\", \"Int\", \"Y/G\", \"Sk\"]"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 64,
-   "id": "cd8c3ca8",
+   "id": "6e82eaae",
    "metadata": {},
    "outputs": [],
    "source": [
     "def predict(data):\n",
-    "    columns = [\"Name\", \"G\", \"GS\", \"Cmp\", \"Att\", \"Yds\", \"Cmp%\", \"TD\", \"Int\", \"Y/G\", \"Sk\"]\n",
     "    row = df[df[\"Name\"] == data]\n",
     "    row = row.loc[:, ~df.columns.str.contains('^Unnamed')]\n",
     "    if not len(row):\n",
@@ -48,7 +48,7 @@
   {
    "cell_type": "code",
    "execution_count": 81,
-   "id": "fae5cc55",
+   "id": "b9242a91",
    "metadata": {},
    "outputs": [
     {
@@ -92,6 +92,7 @@
     "                    ],\n",
     "                    title=\"Rookie QB Career Prediction (Name)\",\n",
     "                    description=\"Given Name of QB who has played in the NFL, predict their career tier. Uses data from https:\\/\\/www.pro-football-reference.com. Tiers based on PFR Approximate Value.\",\n",
+    "                    article=\"See more details at https://github.com/mhrice/Rookie-QB-Predictions\"\n",
     "                    examples=[\"Tom Brady\", \"Joe Burrow\", \"Trevor Lawrence\"]\n",
     "                   )\n",
     "\n",
@@ -101,7 +102,7 @@
   {
    "cell_type": "code",
    "execution_count": 72,
-   "id": "226cfde1",
+   "id": "46d819f7",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -116,7 +117,7 @@
   {
    "cell_type": "code",
    "execution_count": 80,
-   "id": "66f66ad7",
+   "id": "dd0aae3a",
    "metadata": {},
    "outputs": [
     {
@@ -157,6 +158,7 @@
     "                    outputs=gr.Textbox(label=\"Prediction\"),\n",
     "                    title=\"Rookie QB Career Prediction (Stats)\",\n",
     "                    description=\"Given stats of a presumed rookie QB, predict their career tier. Uses data from https:\\/\\/www.pro-football-reference.com. Tiers based on PFR Approximate Value.\"\n",
+    "                    article=\"See more details at https://github.com/mhrice/Rookie-QB-Predictions\"\n",
     "                    )\n",
     "\n",
     "demo2.launch()"
@@ -165,7 +167,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d6cf6ff1",
+   "id": "5c7e8cbe",
    "metadata": {},
    "outputs": [],
    "source": []

app.py

@@ -0,0 +1,31 @@
+from fastai.tabular.all import *
+import gradio as gr
+
+path = Path()
+df = pd.read_csv("rookie_year.csv")
+learn = load_learner(path/"export.pkl")
+columns = ["Name", "G", "GS", "Cmp", "Att", "Yds", "Cmp%", "TD", "Int", "Y/G", "Sk"]
+
+def predict(data):
+    row = df[df["Name"] == data]
+    row = row.loc[:, ~df.columns.str.contains('^Unnamed')]
+    if not len(row):
+        print("ERROR: No QB in database with this name")
+        return        
+    pred_row, clas, probs = learn.predict(row.iloc[0])
+    prediction = pred_row.decode()["Tier"].item()    
+    return row[columns], prediction
+
+demo = gr.Interface(fn=predict, 
+                    inputs="text", 
+                    outputs=[
+                        gr.Dataframe(row_count=1, col_count=11, headers=columns, label="Rookie Year Stats"), 
+                        gr.Textbox(label="Prediction")
+                    ],
+                    title="Rookie QB Career Prediction (Name)",
+                    description="Given Name of QB who has played in the NFL, predict their career tier. Uses data from https:\/\/www.pro-football-reference.com. Tiers based on PFR Approximate Value.",
+                    article="See more details at https://github.com/mhrice/Rookie-QB-Predictions"
+                    examples=["Tom Brady", "Joe Burrow", "Trevor Lawrence"]
+                   )
+
+demo.launch()