1.-Data-Processing.md

@@ -30,7 +30,35 @@ These locations are used for model training:
 - (52.2297, 21.0122)    # Warsaw, Poland
 
 
+these are the new locations with more variety of temperature ranges
 
+- (48.3330, 16.6319),   # Vienna, Austria
+- (64.1355, -21.8954),  # Reykjavik, Iceland
+- (35.1667, 33.3667),   # Nicosia, Cyprus
+- (59.3293, 18.0686),   # Stockholm, Sweden
+- (41.3851, 2.1734),    # Barcelona, Spain
+- (55.6761, 12.5683),   # Copenhagen, Denmark
+- (37.9838, 23.7275),   # Athens, Greece
+- (53.3498, -6.2603),   # Dublin, Ireland
+- (50.0755, 14.4378),   # Prague, Czech Republic
+- (45.4408, 12.3155),   # Venice, Italy
+- (60.1695, 24.9354),   # Helsinki, Finland
+- (51.5074, -0.1278),   # London, United Kingdom
+- (40.4168, -3.7038),   # Madrid, Spain
+- (43.7102, 7.2620),    # Nice, France
+- (50.8503, 4.3517),    # Brussels, Belgium
+- (42.6977, 23.3219),   # Sofia, Bulgaria
+- (46.2044, 6.1432),    # Geneva, Switzerland
+- (44.4268, 26.1025),   # Bucharest, Romania
+- (52.2297, 21.0122),   # Warsaw, Poland
+- (37.0755, 15.2866),   # Sicily, Italy, hottest in europe
+- (67.5689, 49.3333),   # Komi Republic, Russia, coldest in europe
+- (41.6941, 49.9469),   # Caspian Sea Shoreline, Russia, lowest altitude
+- (43.3499, 42.4453),   # Caucasus Mountains, Russia, highest altitude
+- (81.8000, 25.0000),   # Svalbard Archipelago, Norway, northernmost point in Europe
+- (34.6000, 24.1000),   # Gavdos Island, Greece, southernmost point in Europe
+- (39.4550, -31.2720),  # Azores, Portugal, westernmost point in Europe
+- (67.9340, 68.7060)    # Ural Mountains, Russia, easternmost point in Europe
 
 and these for model validation:
 
@@ -41,6 +69,8 @@ and these for model validation:
 - (56.9496, 24.1052),   # Riga, Latvia
 - (48.1486, 17.1077),   # Bratislava, Slovakia
 - (44.7871, 20.4572)   # Belgrade, Serbia
+- (55.7558, 37.6176)    # Moscow, Russia
+
 
 
 
@@ -65,6 +95,8 @@ After separating time index and feature engineering the dataframe consists of th
 - 'global_tilted_irradiance', 
 - 'lat', 
 - 'lon' 
+- 'alt'
+after feedback I also fetched altitude of the locations from Open-Elevation API
 
 **time**
 - 'hour', 
@@ -123,4 +155,51 @@ After separating time index and feature engineering the dataframe consists of th
 - '365d_rolling_min', 
 - '365d_rolling_std'
 
-Afterwards sequences for the model are created.
+Afterwards I normalize and scale the data with a MinMaxScaler.
+
+
+
+With this code the sequences with sequence length = 6 and param = 'T2M' for the model are created.
+```
+    X_train, y_train = [], []
+    for i in range(len(train_df) - sequence_length - hours_to_predict + 1):
+        X_train.append(train_df.iloc[i:(i + sequence_length)].values)
+        if include_target:
+            y_train.append(train_df.iloc[i + sequence_length:i + sequence_length + hours_to_predict][param].values)
+    if include_target:
+        X_train = np.array(X_train)
+        y_train = np.array(y_train)
+
+    # Reshape for ConvLSTM
+    X_train = X_train.reshape((X_train.shape[0], sequence_length, X_train.shape[2]))
+```
+Output of all_sequences[0][0][0]
+
+```
+array([[0.63587862, 0.65751672, 0.79055085, 0.        , 0.67400501,
+        0.90413209, 0.        , 0.21135455, 0.38957586, 0.        ,
+        0.        , 0.29095339, 0.47914441, 0.03654058, 0.95652174,
+        0.24383562, 0.23076923, 0.18181818, 0.        , 0.25      ,
+        0.9330127 , 1.        , 0.5       , 0.99988888, 0.51074899,
+        0.73202077, 0.        , 0.12808288, 0.52656207, 0.63587862,
+        0.63587862, 0.63587862, 0.63587862, 0.63587862, 0.63587862,
+        0.65751672, 0.65751672, 0.5165877 , 0.54142189, 0.        ,
+        0.        , 0.63982648, 0.64717827, 0.66373074, 0.68086505,
+        0.76426509, 0.73619747, 0.73650485, 0.74377425, 0.44403896,
+        0.75644639, 0.83379982, 0.60455111, 0.45051796],
+[2],
+[3],
+[4],
+[5],
+       [0.62444538, 0.64383824, 0.77791441, 0.        , 0.65537662,
+        0.90025098, 0.        , 0.23389022, 0.3841674 , 0.        ,
+        0.        , 0.29095339, 0.47914441, 0.03654058, 0.13043478,
+        0.24657534, 0.23076923, 0.27272727, 0.        , 0.85355339,
+        0.85355339, 0.9330127 , 0.25      , 1.        , 0.50214255,
+        0.71990323, 0.        , 0.12808288, 0.52720481, 0.62934533,
+        0.63587862, 0.63587862, 0.63587862, 0.63587862, 0.63587862,
+        0.62267959, 0.6090057 , 0.51184839, 0.55437695, 0.        ,
+        0.        , 0.63194027, 0.64175095, 0.6603341 , 0.67889608,
+        0.76425445, 0.73619747, 0.73650485, 0.74377425, 0.44403896,
+        0.75644639, 0.83379982, 0.60455111, 0.45051796]])
+```