first commit

predict.py

@@ -0,0 +1,94 @@
+import pandas as pd
+import numpy as np
+from datetime import datetime, timedelta
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_absolute_error, mean_absolute_percentage_error
+import gradio as gr
+
+# Charger et préparer les données
+df = pd.read_csv("datatset/sphist.csv")
+df['Date'] = pd.to_datetime(df["Date"])
+df = df.sort_values(by='Date', ascending=True)
+
+year_i = -1
+day_i = -1
+mean_d = np.nan
+std_d = np.nan
+std_d_v = np.nan
+df['std 5'] = np.nan
+df['mean 5'] = np.nan
+mean_y = np.nan
+std_y = np.nan
+ratio = np.nan
+df['mean 365'] = np.nan
+df['std 365'] = np.nan
+j = 0
+for i, elt in df.iterrows():
+    if df.iloc[j]['Date'] - df.iloc[0]['Date'] > timedelta(days=365):
+        if year_i == -1:
+            year_i = 0
+        mean_y = np.mean(df.iloc[year_i:j]['Open'])
+        std_y = np.std(df.iloc[year_i:j]['Open'])
+        year_i += 1
+    df.iloc[j, df.columns.get_loc("std 365")] = std_y
+    df.iloc[j, df.columns.get_loc("mean 365")] = mean_y
+    if df.iloc[j]['Date'] - df.iloc[0]['Date'] > timedelta(days=5):
+        if day_i == -1:
+            day_i = 0
+        mean_d = np.mean(df.iloc[day_i:j]["Open"])
+        std_d = np.std(df.iloc[day_i:j]['Open'])
+        std_d_v = np.std(df.iloc[day_i:j]['Volume'])
+        day_i += 1
+    df.iloc[j, df.columns.get_loc("mean 5")] = mean_d
+    df.iloc[j, df.columns.get_loc("std 5")] = std_d
+    j += 1
+
+# Ajouter des indicateurs utiles pour notre modèle de ML
+df['5 Days Open'] = df['Open'].rolling(center=False, window=5).mean()
+df['Year'] = df['Date'].apply(lambda x: x.year)
+df['5 Days High'] = df['High'].rolling(center=False, window=5).mean()
+df['5 Days Low'] = df['Low'].rolling(center=False, window=5).mean()
+df['5 Days Volume'] = df['Volume'].rolling(center=False, window=5).mean()
+
+# Déplacer la colonne d'un jour
+df['5 Days Open'] = df['5 Days Open'].shift(1)
+df = df.dropna(axis=0)
+df = df.drop(df[df["Date"] < datetime(year=1951, month=1, day=3)].index, axis=0)
+test = df[df['Date'] >= datetime(year=2013, month=1, day=1)]
+train = df[df['Date'] < datetime(year=2013, month=1, day=1)]
+
+# Entraîner le modèle
+lr = LinearRegression().fit(train.drop(columns=["Open", 'High', 'Low', 'Volume', 'Adj Close', 'Close', 'Date']), train["Close"])
+pred = lr.predict(test.drop(columns=["Open", 'High', 'Low', 'Volume', 'Adj Close', 'Close', 'Date']))
+
+# Calculer les erreurs
+err = mean_absolute_error(test["Close"], pred)
+errP = mean_absolute_percentage_error(test["Close"], pred)
+
+# Créer le DataFrame pour le tableau
+result_df = pd.DataFrame({'Predictions': pred, 'Actual Close': test['Close']})
+
+# Fonction pour afficher l'erreur et le tableau
+def display_results():
+    return str(err), str(errP), result_df
+
+# Créer l'interface Gradio
+with gr.Blocks() as demo:
+    gr.Markdown("# Linear Regression Model Results")
+    gr.Markdown("""This model was trained on S&P 500 stock price before 2013. The predictions below are taken betweek 2013 and 2015.
+                
+    0.4% of average error was reached using LinearRegression.""")
+    with gr.Row():
+        with gr.Column():
+            error = gr.Textbox(label="Mean Absolute Error")
+            errorP = gr.Textbox(label="Mean Absolute Percentage Error")
+            table = gr.Dataframe(label="Predictions vs Actual Close Prices")
+
+    with gr.Row():
+        with gr.Column():
+            btn = gr.Button("Show Results")
+
+    btn.click(display_results, outputs=[error, errorP, table])
+
+# Lancer l'interface Gradio
+demo.launch()