diff --git a/plot.py b/plot.py
index f40f06e..e5b8228 100644
--- a/plot.py
+++ b/plot.py
@@ -1,36 +1,57 @@
-import sys
+import os
 import pandas as pd
 from datetime import datetime
 import csv
+import datetime
 import matplotlib.pyplot as plt
 import matplotlib.ticker as mtick
 import matplotlib.dates as mdates
-from matplotlib.backends.backend_pdf import PdfPages
-headers = ['Phase', 'Method', 'Start episodes', 'Episodes', 'Sum', 'Mean']
 
-fig, ax = plt.subplots(1, 1)
+train_headers = ['timestamp', 'eps_train', 'eps_trained_session', 'sum', 'mean']
+eval_headers  = ['timestamp', 'method', 'eps_train', 'eval_eps_used', 'sum', 'mean']
 
-plt.ion()
-plt.title('Mean over episodes')
-plt.xlabel('Episodes')
-plt.ylabel('Mean')
-plt.grid(True)
+model_path = 'models'
 
-#ax.set_xlim(left=0)
-ax.set_ylim([-2, 2])
 
-plt.show()
-
-while True:
-    #df = pd.read_csv(sys.stdin, sep=";", names=headers)
-    df = pd.read_csv('log', sep=";", names=headers)
-    df['Total episodes'] = df['Start episodes'] + 100
-
-    print(df)
+def dataframes(model_name):
+    def df_timestamp_to_datetime(df):
+        df['timestamp'] = df['timestamp'].map(lambda t: datetime.datetime.fromtimestamp(t))
+        return df
     
-    x = df['Total episodes']
-    y = df['Mean']
+    log_path = os.path.join(model_path, model_name, 'logs')
+    raw_dfs = [ pd.read_csv(os.path.join(log_path, 'eval.log'), sep=';', names=eval_headers),
+                pd.read_csv(os.path.join(log_path, 'train.log'), sep=';', names=train_headers) ]
+    dfs = [ df_timestamp_to_datetime(df) for df in raw_dfs ]
+    dataframes = {
+        'eval': dfs[0],
+        'train': dfs[1] 
+    }
+    return dataframes
+
+
+if __name__ == '__main__':
+    fig, ax = plt.subplots(1, 1)
+
+    plt.ion()
+    plt.title('Mean over episodes')
+    plt.xlabel('Episodes trained')
+    plt.ylabel('Mean')
+    plt.grid(True)
+
+    #ax.set_xlim(left=0)
+    ax.set_ylim([-2, 2])
+
+    plt.show()
+
+    while True:
+        df = pd.read_csv('models/c/logs/eval.log', sep=";", names=eval_headers)
+        df['timestamp'] = df['timestamp'].map(lambda t: datetime.datetime.fromtimestamp(t))
+
+        print(df)
+        
+        x = df['eps_train']
+        y = df['mean']
     
-    plt.scatter(x, y, c=[[1,0.5,0]])
-    #fig.canvas.draw()
-    plt.pause(2)
+        plt.scatter(x, y, c=[[1, 0.5, 0]])
+        #fig.canvas.draw()
+        plt.pause(2)