refactor the name of the dataset file

README.md

@@ -14,8 +14,10 @@ how to git? do not `push --force`. prefer pull requests. its like github
 
 we will plan to do this in multiple different ways using scikit-learn and pytorch. tensorflow is ancient.
 
-> [!IMPORTANT]
+> [!NOTE]
-> phase out tensorflow. dont use it.
+> ~phase out tensorflow. dont use it.~
+>
+> its 2 different platforms for 2 different types of people. use whatever ig
 
 maybe also fit more weather related stats? this dataset is taken from nasa so sources are there
 

dataset_update.py

@@ -1,10 +1,11 @@
 import urllib.parse
 import urllib.request
 from datetime import datetime
+from global_config import DATA_FILE_NAME
 
 # Define parameters
 latitude, longitude = 21.04815477090267, 105.80123159165096  # lmao
-start_date = "2010-01-01"
+start_date = "1981-01-01"
 end_date = datetime.now().strftime("%Y-%m-%d")  # Today's date
 
 # Define desired parameters
@@ -16,9 +17,11 @@ end_date = datetime.now().strftime("%Y-%m-%d")  # Today's date
 # WS10M           MERRA-2 Wind Speed at 10 Meters (m/s)
 # WD10M           MERRA-2 Wind Direction at 10 Meters (Degrees)
 # more at https://power.larc.nasa.gov/data-access-viewer/
+weather_params = ["QV2M"]
+
 
 params = {
-    "parameters": "QV2M,T2M,PRECTOTCORR",
+    "parameters": ",".join(weather_params),
     "community": "RE",
     "longitude": longitude,
     "latitude": latitude,
@@ -40,7 +43,7 @@ try:
     with urllib.request.urlopen(url) as response:
         if response.status == 200:
             csv_data = response.read().decode("utf-8")
-            with open("hanoi_weather_data.csv", "w", encoding="utf-8") as file:
+            with open(DATA_FILE_NAME, "w", encoding="utf-8") as file:
                 file.write(csv_data)
             print("Data successfully downloaded and saved to 'hanoi_weather_data.csv'.")
         else:

global_config.py

@@ -0,0 +1 @@
+DATA_FILE_NAME = "hanoi_weather_data.csv"

load_data.py

@@ -7,6 +7,8 @@ from typing import Union
 
 import pandas as pd
 
+from global_config import DATA_FILE_NAME
+
 
 def cut_headers(stream: Union[io.StringIO, io.FileIO, io.TextIOWrapper]):
     headers = []
@@ -73,15 +75,18 @@ def validate_view(data: pd.DataFrame, verbose=False):
     return data
 
 
-# if __name__ == "__main__":
+def load_this_data(filename=DATA_FILE_NAME, verbose=False, *a):
-def load_this_data(filename, verbose=False):
+    d = load_data(filename, *a)
-    d = load_data(filename)
     # if verbose:
     #     print(d.columns)
     d = date_combine(d)
     # if verbose:
     #     print(d.columns)
     d = validate_view(d, verbose)
-    # if verbose:
+    if verbose:
+        print(d.head())
     #     print(d.columns)
     return d
+
+if __name__ == "__main__":
+    load_this_data(verbose=True)

main.ipynb

@@ -138,7 +138,8 @@
       ],
       "source": [
         "# data_file = \"hanoi_qv2m_latest.csv\"\n",
-        "data_file = \"dataset.csv\"\n",
+        "# data_file = \"dataset.csv\"\n",
+        "from global_config import DATA_FILE_NAME as data_file\n",
         "\n",
         "data = pd.read_csv(\n",
         "    data_file,\n",

pytorch_port.py

@@ -8,7 +8,7 @@ from sklearn.preprocessing import MinMaxScaler
 import numpy as np
 from load_data import load_this_data
 
-a = load_this_data("dataset.csv")
+a = load_this_data()
 
 # time series forecasting
 
@@ -19,6 +19,7 @@ scaled_data = scaler.fit_transform(a)
 
 
 def create_sequences(data, seq_length):
+    "see this? return[0] is the big x and return[1] is the big y. and h(x) = y. and h(x) is the model."
     xs = []
     ys = []
     for i in range(len(data) - seq_length):

rr.md

@@ -1 +0,0 @@
->no ewy