fix(data.py): precipication value was same as temp

data.py

@@ -35,7 +35,7 @@ for year in range(MIN_YEAR, MAX_YEAR + 1):
     temp[year] = read_temp_data(year)
     precip[year] = read_precip_data(year)
     precip[year]['yearly_avg'] = precip[year].mean(axis=1)
-
+    
 
 world = geopandas.read_file(geopandas.datasets.get_path('naturalearth_lowres'))[['geometry']].unary_union
 boundary = world.boundary
@@ -87,16 +87,16 @@ def get_point_information(longitude, latitude):
         autumn_precip = [yp[month] for month in AUTUMN_MONTHS]
 
         item['temp_winter_{}'.format(year)] = np.mean(winter_temp)
-        item['precip_winter_{}'.format(year)] = np.mean(winter_temp)
+        item['precip_winter_{}'.format(year)] = np.mean(winter_precip)
 
         item['temp_spring_{}'.format(year)] = np.mean(spring_temp)
-        item['precip_spring_{}'.format(year)] = np.mean(spring_temp)
+        item['precip_spring_{}'.format(year)] = np.mean(spring_precip)
 
         item['temp_summer_{}'.format(year)] = np.mean(summer_temp)
-        item['precip_summer_{}'.format(year)] = np.mean(summer_temp)
+        item['precip_summer_{}'.format(year)] = np.mean(summer_precip)
 
         item['temp_autumn_{}'.format(year)] = np.mean(autumn_temp)
-        item['precip_autumn_{}'.format(year)] = np.mean(autumn_temp)
+        item['precip_autumn_{}'.format(year)] = np.mean(autumn_precip)
 
     return item
 

nn.py

@@ -13,12 +13,17 @@ from utils import *
 
 tf.enable_eager_execution()
 
-df = pd.read_pickle('data_distance.p')
+df = pd.read_pickle('data_final.p')
 # print(df.head())
 
-dataset = dataframe_to_dataset_biomes(df)
+# dataset = dataframe_to_dataset_biomes(df)
+dataset = dataframe_to_dataset_temp_precip(df)
 
+i = 0
 for feature, target in dataset:
+    i += 1
+    if i > 10:
+        break
     print('{} => {}'.format(feature, target))
 
 print(tf.__version__)

utils.py

@@ -6,6 +6,22 @@ from constants import *
 inputs = ['elevation', 'distance_to_water']
 output = 'biome_num'
 
+def normalize(v):
+    return (v - np.min(v)) / (np.max(v) - np.min(v))
+
+def normalize_ndarray(ar):
+    tr = np.transpose(ar)
+    for i in range(tr.shape[0]):
+        tr[i] = normalize(tr[i])
+
+    return np.transpose(tr)
+
+def normalize_df(df):
+    for col in df.columns:
+        df[col] = normalize(df[col])
+
+    return df
+
 def dataframe_to_dataset_biomes(df):
     rows = df.shape[0]
 
@@ -16,7 +32,6 @@ def dataframe_to_dataset_biomes(df):
     tf_inputs = np.empty((0, columns))
     tf_output = np.empty((0))
     latitude = np.array(df.index.get_level_values(1))
-    longitude = np.array(df.index.get_level_values(0))
 
     for year in range(MIN_YEAR, MAX_YEAR + 1):
         local_inputs = list(inputs)
@@ -33,7 +48,38 @@ def dataframe_to_dataset_biomes(df):
         tf_inputs = np.concatenate((tf_inputs, local_df.values), axis=0)
         tf_output = np.concatenate((tf_output, df[output].values), axis=0)
 
-    tf_inputs = tf.cast(tf_inputs, tf.float32)
-    tf_output = tf.cast(tf_output, tf.int32)
+    tf_inputs = tf.cast(normalize_ndarray(tf_inputs), tf.float32)
+    tf_output = tf.cast(normalize_ndarray(tf_output), tf.int32)
 
     return tf.data.Dataset.from_tensor_slices((tf_inputs, tf_output))
+
+def dataframe_to_dataset_temp_precip(df):
+    rows = df.shape[0]
+
+    # elevation, distance_to_water, latitude
+    # season, year
+    columns = 5
+
+    tf_inputs = np.empty((0, columns))
+    tf_output = np.empty((0, 2))
+    latitude = np.array(df.index.get_level_values(1))
+
+    for year in range(MIN_YEAR, MAX_YEAR + 1):
+        local_inputs = list(inputs)
+
+        for idx, season in enumerate(SEASONS):
+            season_index = idx / len(season)
+            local_df = df[local_inputs]
+            local_df.loc[:, 'latitude'] = pd.Series(latitude, index=local_df.index)
+            local_df.loc[:, 'season'] = pd.Series(np.repeat(season_index, rows), index=local_df.index)
+            local_df.loc[:, 'year'] = pd.Series(np.repeat(year, rows), index=local_df.index)
+
+            output = ['temp_{}_{}'.format(season, year), 'precip_{}_{}'.format(season, year)]
+            tf_inputs = np.concatenate((tf_inputs, local_df.values), axis=0)
+            tf_output = np.concatenate((tf_output, df[output].values), axis=0)
+
+    tf_inputs = tf.cast(normalize_ndarray(tf_inputs), tf.float32)
+    tf_output = tf.cast(normalize_ndarray(tf_output), tf.float32)
+
+    return tf.data.Dataset.from_tensor_slices((tf_inputs, tf_output))
+