not much

.gitignore

@@ -185,4 +185,6 @@ ipython_config.py
 
 
 .conda*/
-dead/
+
+data/
+# for rn

dataset_update.py

@@ -1,13 +1,45 @@
+import sys
 import urllib.parse
 import urllib.request
 from datetime import datetime
+import logging
 from global_config import DATA_FILE_NAME
 
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
+)
+
 # Define parameters
-latitude, longitude = 21.04815477090267, 105.80123159165096  # lmao
+latitude, longitude = 21.04815477090267, 105.80123159165096  # Default: Hanoi
-start_date = "1981-01-01"
+# start_date = "1981-01-01"
+start_date = "2001-01-01"
 end_date = datetime.now().strftime("%Y-%m-%d")  # Today's date
 
+# most used parameters from NASA POWER API:
+# T2M             MERRA-2 Temperature at 2 Meters (C)
+# T2M_MAX         MERRA-2 Maximum Temperature at 2 Meters (C)
+# T2M_MIN         MERRA-2 Minimum Temperature at 2 Meters (C)
+# T2MDEW          MERRA-2 Dew/Frost Point at 2 Meters (C)
+# T2MWET          MERRA-2 Wet Bulb Temperature at 2 Meters (C)
+# PRECTOTCORR     MERRA-2 Precipitation Corrected (mm/day)
+# ALLSKY_SFC_SW_DWN All Sky Surface Shortwave Downward Irradiance (kW-hr/m^2/day)
+# CLRSKY_SFC_SW_DWN Clear Sky Surface Shortwave Downward Irradiance (kW-hr/m^2/day)
+# RH2M            MERRA-2 Relative Humidity at 2 Meters (%)
+# QV2M            MERRA-2 Specific Humidity at 2 Meters (g/kg)
+# PS              MERRA-2 Surface Pressure (kPa)
+# WS10M           MERRA-2 Wind Speed at 10 Meters (m/s)
+# WS50M           MERRA-2 Wind Speed at 50 Meters (m/s)
+# WD10M           MERRA-2 Wind Direction at 10 Meters (Degrees)
+# WD50M           MERRA-2 Wind Direction at 50 Meters (Degrees)
+# TS              MERRA-2 Earth Skin Temperature (C)
+# PRECTOT         MERRA-2 Precipitation (mm/day)
+# ALLSKY_KT       All Sky Insolation Clearness Index (dimensionless)
+# CLRSKY_KT       Clear Sky Insolation Clearness Index (dimensionless)
+# ALLSKY_SFC_LW_DWN All Sky Surface Longwave Downward Irradiance (W/m^2)
+# CLOUD_AMT       Cloud amount (%)
+
+
 # Define desired parameters
 # T2M             MERRA-2 Temperature at 2 Meters (C)
 # PRECTOTCORR     MERRA-2 Precipitation Corrected (mm/day)
@@ -18,21 +50,26 @@ end_date = datetime.now().strftime("%Y-%m-%d")  # Today's date
 # WD10M           MERRA-2 Wind Direction at 10 Meters (Degrees)
 # more at https://power.larc.nasa.gov/data-access-viewer/
 weather_params = [
-    # "T2M",
+    "T2M",
-    # "T2M_MAX",
+    "T2M_MAX",
-    # "T2M_MIN",
+    "T2M_MIN",
-    # "T2MDEW",
+    "T2MDEW",
-    # "PRECTOTCORR",
+    "PRECTOTCORR",
     "QV2M",
-    # "RH2M",
+    "RH2M",
-    # "PS",
+    "PS",
-    # "CLOUD_AMT",
+    "CLOUD_AMT",
-    # "WS10M",
+    "WS10M",
-    # "WD10M",
+    "WD10M",
-    # "ALLSKY_KT",
+    "ALLSKY_KT",
-    # "ALLSKY_SFC_SW_DWN",
+    "ALLSKY_SFC_SW_DWN",
 ]
 
+
+if len(weather_params) > 20:
+    logging.error("too much! %d params bigger than 20", len(weather_params))
+    sys.exit(1)
+
 params = {
     "parameters": ",".join(weather_params),
     "community": "RE",
@@ -53,13 +90,22 @@ url = f"{base_url}?{query_string}"
 
 # Make the API request using urllib
 try:
+    logging.info("Requesting data from NASA POWER API...")
     with urllib.request.urlopen(url) as response:
         if response.status == 200:
-            csv_data = response.read().decode("utf-8")
+            # Save data to file
-            with open(DATA_FILE_NAME, "w", encoding="utf-8") as file:
+            with open(DATA_FILE_NAME, "wb") as file:
-                file.write(csv_data)
+                while chunk := response.read(1024):  # Read 1 KB at a time
-            print("Data successfully downloaded and saved to 'hanoi_weather_data.csv'.")
+                    file.write(chunk)
+            logging.info(
+                "Data successfully downloaded and saved to '%s'.", DATA_FILE_NAME
+            )
         else:
-            print(f"Failed to retrieve data: HTTP Status Code {response.status}")
+            print("re", response.read().decode())
+            logging.error(
+                "Failed to retrieve data: HTTP Status Code %s", response.status
+            )
 except urllib.error.URLError as e:
-    print(f"Failed to retrieve data: {e.reason}")
+    logging.error("Failed to retrieve data: %s", e)
+except Exception as e:
+    logging.error("An unexpected error occurred: %s", e)

global_config.py

@@ -1 +1 @@
-DATA_FILE_NAME = "data/hanoi_weather_data.csv"
+DATA_FILE_NAME = "hanoi_weather_data.csv"

load_data.py

@@ -5,11 +5,16 @@ import io
 # from itertools import islice
 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 = []
     exist_startheader = False
-
+    p99_header = 123 # should there be header
-    while line := stream.readline():
+    while (line := stream.readline()) and p99_header > 0:
         if "-BEGIN HEADER-" in line and not exist_startheader:
             exist_startheader = True
             headers.append(str(line.strip()))
@@ -20,9 +25,71 @@ def cut_headers(stream: Union[io.StringIO, io.FileIO, io.TextIOWrapper]):
             # print(f"{line = }")
             headers.append(str(line.strip()))
         elif not exist_startheader:
-            continue
+            p99_header -= 1
-    if not exist_startheader:
+            # continue
+    if not exist_startheader or p99_header == 0:
         # If no headers are found, reset the stream and return
         stream.seek(0)
         return "", stream
     return "\n".join(headers), stream
+
+
+# if __name__ == "__main__":
+#     with open("hanoi_qv2m_latest.csv", "r", encoding="utf-8") as file:
+#         header, file = cut_headers(file)
+#         print("Extracted Header:")
+#         print(header)
+#         data = pd.read_csv(file)
+#         print("\nFirst 5 Lines of Data:")
+#         print(data.head())
+#         print(data.isnull().sum())
+
+
+def load_data(
+    weather_file_name, columns=["Year", "Month", "Day", "Humidity"].copy(), na=-999
+):
+    with open(weather_file_name, "r", encoding="utf-8") as file:
+        _header, file = cut_headers(file)
+        data = pd.read_csv(file, na_values=na)
+    # print(header)
+    data.columns = columns
+    return data
+
+
+def date_combine(data: pd.DataFrame, verbose=False):
+    data["Date"] = pd.to_datetime(data[["Year", "Month", "Day"]])
+    data = data.drop(columns=["Year", "Month", "Day"])
+    if verbose:
+        print("b4 set index", data.columns)
+    data = data.set_index("Date")
+    if verbose:
+        print("after set index", data.columns)
+
+    return data
+
+
+def validate_view(data: pd.DataFrame, verbose=False):
+    if verbose:
+        print(f"Shape with N/A values: {data.shape}")
+        isn = data.isnull().sum().iloc[0]
+        print(f"Count of N/A values: {isn}")
+    data = data.dropna()  # Drop the rows with missing values
+    if verbose:
+        isn = data.isnull().sum().iloc[0]
+        print(f"Count after drop: {isn}")
+        print(data.describe())
+    return data
+
+
+def load_this_data(filename=DATA_FILE_NAME, verbose=False, *a):
+    d = load_data(filename, *a)
+    d = date_combine(d, verbose)
+    d = validate_view(d, verbose)
+    if verbose:
+        print(d.head())
+        print(d.columns)
+    return d
+
+
+if __name__ == "__main__":
+    load_this_data(verbose=True)

main.ipynb

@@ -66,17 +66,17 @@
       "cell_type": "code",
       "execution_count": 2,
       "metadata": {
-        "id": "9vfz_tsewSmD",
-        "outputId": "2efacccd-4025-444c-ab48-34ae58e55462",
         "colab": {
           "base_uri": "https://localhost:8080/",
           "height": 551
-        }
+        },
+        "id": "9vfz_tsewSmD",
+        "outputId": "2efacccd-4025-444c-ab48-34ae58e55462"
       },
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "-BEGIN HEADER-\n",
             "\n",
@@ -98,17 +98,12 @@
           ]
         },
         {
-          "output_type": "execute_result",
           "data": {
-            "text/plain": [
+            "application/vnd.google.colaboratory.intrinsic+json": {
-              "            Humidity\n",
+              "summary": "{\n  \"name\": \"data\",\n  \"rows\": 16197,\n  \"fields\": [\n    {\n      \"column\": \"Date\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"1981-01-01 00:00:00\",\n        \"max\": \"2025-05-06 00:00:00\",\n        \"num_unique_values\": 16197,\n        \"samples\": [\n          \"2008-04-18 00:00:00\",\n          \"1983-12-23 00:00:00\",\n          \"1990-11-18 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Humidity\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 4.796305273033087,\n        \"min\": 3.15,\n        \"max\": 23.39,\n        \"num_unique_values\": 1864,\n        \"samples\": [\n          17.59,\n          16.12,\n          18.47\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
-              "Date                \n",
+              "type": "dataframe",
-              "1981-01-01      9.57\n",
+              "variable_name": "data"
-              "1981-01-02      8.51\n",
+            },
-              "1981-01-03      7.24\n",
-              "1981-01-04      9.20\n",
-              "1981-01-05     11.80"
-            ],
             "text/html": [
               "\n",
               "  <div id=\"df-7d81f82a-224a-4844-87a0-190aa05ad2ef\" class=\"colab-df-container\">\n",
@@ -371,14 +366,19 @@
               "    </div>\n",
               "  </div>\n"
             ],
-            "application/vnd.google.colaboratory.intrinsic+json": {
+            "text/plain": [
-              "type": "dataframe",
+              "            Humidity\n",
-              "variable_name": "data",
+              "Date                \n",
-              "summary": "{\n  \"name\": \"data\",\n  \"rows\": 16197,\n  \"fields\": [\n    {\n      \"column\": \"Date\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"1981-01-01 00:00:00\",\n        \"max\": \"2025-05-06 00:00:00\",\n        \"num_unique_values\": 16197,\n        \"samples\": [\n          \"2008-04-18 00:00:00\",\n          \"1983-12-23 00:00:00\",\n          \"1990-11-18 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Humidity\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 4.796305273033087,\n        \"min\": 3.15,\n        \"max\": 23.39,\n        \"num_unique_values\": 1864,\n        \"samples\": [\n          17.59,\n          16.12,\n          18.47\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
+              "1981-01-01      9.57\n",
-            }
+              "1981-01-02      8.51\n",
+              "1981-01-03      7.24\n",
+              "1981-01-04      9.20\n",
+              "1981-01-05     11.80"
+            ]
           },
+          "execution_count": 2,
           "metadata": {},
-          "execution_count": 2
+          "output_type": "execute_result"
         }
       ],
       "source": [
@@ -420,22 +420,22 @@
       "cell_type": "code",
       "execution_count": 3,
       "metadata": {
-        "id": "KGuNRxutwSmE",
-        "outputId": "c676b5a0-1b45-42ff-a23e-5e98d506c273",
         "colab": {
           "base_uri": "https://localhost:8080/"
-        }
+        },
+        "id": "KGuNRxutwSmE",
+        "outputId": "c676b5a0-1b45-42ff-a23e-5e98d506c273"
       },
       "outputs": [
         {
-          "output_type": "execute_result",
           "data": {
             "text/plain": [
               "(16197, 1)"
             ]
           },
+          "execution_count": 3,
           "metadata": {},
-          "execution_count": 3
+          "output_type": "execute_result"
         }
       ],
       "source": [
@@ -445,23 +445,18 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 4,
+      "execution_count": null,
       "metadata": {
-        "id": "gtFfTZ-fwSmE",
-        "outputId": "d304b35d-5e95-47e2-b0eb-b187b47984c8",
         "colab": {
           "base_uri": "https://localhost:8080/",
           "height": 115
-        }
+        },
+        "id": "gtFfTZ-fwSmE",
+        "outputId": "d304b35d-5e95-47e2-b0eb-b187b47984c8"
       },
       "outputs": [
         {
-          "output_type": "execute_result",
           "data": {
-            "text/plain": [
-              "Humidity    3\n",
-              "dtype: int64"
-            ],
             "text/html": [
               "<div>\n",
               "<style scoped>\n",
@@ -492,36 +487,36 @@
               "  </tbody>\n",
               "</table>\n",
               "</div><br><label><b>dtype:</b> int64</label>"
+            ],
+            "text/plain": [
+              "Humidity    3\n",
+              "dtype: int64"
             ]
           },
+          "execution_count": 4,
           "metadata": {},
-          "execution_count": 4
+          "output_type": "execute_result"
         }
       ],
       "source": [
-        "data.isnull().sum()\n",
+        "data.isna().sum()\n",
         "# There are 3 missing values in Humidity column"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 5,
+      "execution_count": null,
       "metadata": {
-        "id": "yJuOfNUrwSmE",
-        "outputId": "a1614ee6-5680-4f54-bcfd-769a9a78943f",
         "colab": {
           "base_uri": "https://localhost:8080/",
           "height": 115
-        }
+        },
+        "id": "yJuOfNUrwSmE",
+        "outputId": "a1614ee6-5680-4f54-bcfd-769a9a78943f"
       },
       "outputs": [
         {
-          "output_type": "execute_result",
           "data": {
-            "text/plain": [
-              "Humidity    0\n",
-              "dtype: int64"
-            ],
             "text/html": [
               "<div>\n",
               "<style scoped>\n",
@@ -552,10 +547,15 @@
               "  </tbody>\n",
               "</table>\n",
               "</div><br><label><b>dtype:</b> int64</label>"
+            ],
+            "text/plain": [
+              "Humidity    0\n",
+              "dtype: int64"
             ]
           },
+          "execution_count": 5,
           "metadata": {},
-          "execution_count": 5
+          "output_type": "execute_result"
         }
       ],
       "source": [
@@ -567,28 +567,20 @@
       "cell_type": "code",
       "execution_count": 6,
       "metadata": {
-        "id": "ODdNZOukwSmF",
-        "outputId": "f54da03b-895c-4027-9116-d76e88c093ad",
         "colab": {
           "base_uri": "https://localhost:8080/",
           "height": 300
-        }
+        },
+        "id": "ODdNZOukwSmF",
+        "outputId": "f54da03b-895c-4027-9116-d76e88c093ad"
       },
       "outputs": [
         {
-          "output_type": "execute_result",
           "data": {
-            "text/plain": [
+            "application/vnd.google.colaboratory.intrinsic+json": {
-              "           Humidity\n",
+              "summary": "{\n  \"name\": \"data\",\n  \"rows\": 8,\n  \"fields\": [\n    {\n      \"column\": \"Humidity\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5720.786588664725,\n        \"min\": 3.15,\n        \"max\": 16194.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          14.918440163023341,\n          15.57,\n          16194.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
-              "count  16194.000000\n",
+              "type": "dataframe"
-              "mean      14.918440\n",
+            },
-              "std        4.796305\n",
-              "min        3.150000\n",
-              "25%       11.150000\n",
-              "50%       15.570000\n",
-              "75%       19.310000\n",
-              "max       23.390000"
-            ],
             "text/html": [
               "\n",
               "  <div id=\"df-3372d7c2-bbe3-491a-9a48-20a3092647a3\" class=\"colab-df-container\">\n",
@@ -859,13 +851,21 @@
               "    </div>\n",
               "  </div>\n"
             ],
-            "application/vnd.google.colaboratory.intrinsic+json": {
+            "text/plain": [
-              "type": "dataframe",
+              "           Humidity\n",
-              "summary": "{\n  \"name\": \"data\",\n  \"rows\": 8,\n  \"fields\": [\n    {\n      \"column\": \"Humidity\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5720.786588664725,\n        \"min\": 3.15,\n        \"max\": 16194.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          14.918440163023341,\n          15.57,\n          16194.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
+              "count  16194.000000\n",
-            }
+              "mean      14.918440\n",
+              "std        4.796305\n",
+              "min        3.150000\n",
+              "25%       11.150000\n",
+              "50%       15.570000\n",
+              "75%       19.310000\n",
+              "max       23.390000"
+            ]
           },
+          "execution_count": 6,
           "metadata": {},
-          "execution_count": 6
+          "output_type": "execute_result"
         }
       ],
       "source": [
@@ -887,33 +887,33 @@
       "cell_type": "code",
       "execution_count": 7,
       "metadata": {
-        "id": "F_GnBSNPwSmF",
-        "outputId": "b3ae5237-1ead-4d3b-dbe4-fd3415e3be51",
         "colab": {
           "base_uri": "https://localhost:8080/",
           "height": 444
-        }
+        },
+        "id": "F_GnBSNPwSmF",
+        "outputId": "b3ae5237-1ead-4d3b-dbe4-fd3415e3be51"
       },
       "outputs": [
         {
-          "output_type": "execute_result",
           "data": {
             "text/plain": [
               "<matplotlib.legend.Legend at 0x7c5c365680d0>"
             ]
           },
+          "execution_count": 7,
           "metadata": {},
-          "execution_count": 7
+          "output_type": "execute_result"
         },
         {
-          "output_type": "display_data",
           "data": {
+            "image/png": "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 truncated
             "text/plain": [
               "<Figure size 2000x500 with 1 Axes>"
-            ],
+            ]
-            "image/png": "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 truncated
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         }
       ],
       "source": [
@@ -937,23 +937,23 @@
       "cell_type": "code",
       "execution_count": 8,
       "metadata": {
-        "id": "qL3DAMVOwSmF",
-        "outputId": "4a1a8687-7e28-4ae0-8c4c-1b1dec21f004",
         "colab": {
           "base_uri": "https://localhost:8080/",
           "height": 314
-        }
+        },
+        "id": "qL3DAMVOwSmF",
+        "outputId": "4a1a8687-7e28-4ae0-8c4c-1b1dec21f004"
       },
       "outputs": [
         {
-          "output_type": "display_data",
           "data": {
+            "image/png": "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 truncated
             "text/plain": [
               "<Figure size 1500x300 with 2 Axes>"
-            ],
+            ]
-            "image/png": "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 truncated
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         }
       ],
       "source": [
@@ -1014,22 +1014,22 @@
       "cell_type": "code",
       "execution_count": 12,
       "metadata": {
-        "id": "sZHbbu6QwSmG",
-        "outputId": "26b04185-11a0-4d02-9f7d-05afe5ead8c9",
         "colab": {
           "base_uri": "https://localhost:8080/"
-        }
+        },
+        "id": "sZHbbu6QwSmG",
+        "outputId": "26b04185-11a0-4d02-9f7d-05afe5ead8c9"
       },
       "outputs": [
         {
-          "output_type": "execute_result",
           "data": {
             "text/plain": [
               "((12955, 1), (3239, 1))"
             ]
           },
+          "execution_count": 12,
           "metadata": {},
-          "execution_count": 12
+          "output_type": "execute_result"
         }
       ],
       "source": [
@@ -1121,45 +1121,29 @@
       "cell_type": "code",
       "execution_count": 16,
       "metadata": {
-        "id": "hYq8SOknwSmI",
-        "outputId": "c233d7a4-d35d-4cd4-d152-9e80dab70ce7",
         "colab": {
           "base_uri": "https://localhost:8080/",
           "height": 300
-        }
+        },
+        "id": "hYq8SOknwSmI",
+        "outputId": "c233d7a4-d35d-4cd4-d152-9e80dab70ce7"
       },
       "outputs": [
         {
-          "output_type": "display_data",
           "data": {
-            "text/plain": [
-              "\u001b[1mModel: \"sequential\"\u001b[0m\n"
-            ],
             "text/html": [
               "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
               "</pre>\n"
+            ],
+            "text/plain": [
+              "\u001b[1mModel: \"sequential\"\u001b[0m\n"
             ]
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         },
         {
-          "output_type": "display_data",
           "data": {
-            "text/plain": [
-              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
-              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
-              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
-              "│ lstm (\u001b[38;5;33mLSTM\u001b[0m)                     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m64\u001b[0m)        │        \u001b[38;5;34m16,896\u001b[0m │\n",
-              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-              "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m64\u001b[0m)        │             \u001b[38;5;34m0\u001b[0m │\n",
-              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-              "│ lstm_1 (\u001b[38;5;33mLSTM\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m64\u001b[0m)        │        \u001b[38;5;34m33,024\u001b[0m │\n",
-              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-              "│ lstm_2 (\u001b[38;5;33mLSTM\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │        \u001b[38;5;34m33,024\u001b[0m │\n",
-              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-              "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │            \u001b[38;5;34m65\u001b[0m │\n",
-              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
-            ],
             "text/html": [
               "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
               "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
@@ -1175,48 +1159,64 @@
               "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)              │            <span style=\"color: #00af00; text-decoration-color: #00af00\">65</span> │\n",
               "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
               "</pre>\n"
+            ],
+            "text/plain": [
+              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
+              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+              "│ lstm (\u001b[38;5;33mLSTM\u001b[0m)                     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m64\u001b[0m)        │        \u001b[38;5;34m16,896\u001b[0m │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m64\u001b[0m)        │             \u001b[38;5;34m0\u001b[0m │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ lstm_1 (\u001b[38;5;33mLSTM\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m100\u001b[0m, \u001b[38;5;34m64\u001b[0m)        │        \u001b[38;5;34m33,024\u001b[0m │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ lstm_2 (\u001b[38;5;33mLSTM\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │        \u001b[38;5;34m33,024\u001b[0m │\n",
+              "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+              "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │            \u001b[38;5;34m65\u001b[0m │\n",
+              "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
             ]
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         },
         {
-          "output_type": "display_data",
           "data": {
-            "text/plain": [
-              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m83,009\u001b[0m (324.25 KB)\n"
-            ],
             "text/html": [
               "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">83,009</span> (324.25 KB)\n",
               "</pre>\n"
+            ],
+            "text/plain": [
+              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m83,009\u001b[0m (324.25 KB)\n"
             ]
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         },
         {
-          "output_type": "display_data",
           "data": {
-            "text/plain": [
-              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m83,009\u001b[0m (324.25 KB)\n"
-            ],
             "text/html": [
               "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">83,009</span> (324.25 KB)\n",
               "</pre>\n"
+            ],
+            "text/plain": [
+              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m83,009\u001b[0m (324.25 KB)\n"
             ]
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         },
         {
-          "output_type": "display_data",
           "data": {
-            "text/plain": [
-              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
-            ],
             "text/html": [
               "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
               "</pre>\n"
+            ],
+            "text/plain": [
+              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
             ]
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         }
       ],
       "source": [
@@ -1260,16 +1260,16 @@
       "cell_type": "code",
       "execution_count": 18,
       "metadata": {
-        "id": "6JOTZ3zjwSmI",
-        "outputId": "142b6860-b4cc-46aa-ec32-40400202fe1d",
         "colab": {
           "base_uri": "https://localhost:8080/"
-        }
+        },
+        "id": "6JOTZ3zjwSmI",
+        "outputId": "142b6860-b4cc-46aa-ec32-40400202fe1d"
       },
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "Epoch 1/100\n",
             "\u001b[1m101/101\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 25ms/step - loss: 0.0553 - val_loss: 0.0189 - learning_rate: 0.0010\n",
@@ -1474,14 +1474,14 @@
           ]
         },
         {
-          "output_type": "execute_result",
           "data": {
             "text/plain": [
               "<keras.src.callbacks.history.History at 0x7c5c43602a10>"
             ]
           },
+          "execution_count": 18,
           "metadata": {},
-          "execution_count": 18
+          "output_type": "execute_result"
         }
       ],
       "source": [
@@ -1518,16 +1518,16 @@
       "cell_type": "code",
       "execution_count": 19,
       "metadata": {
-        "id": "wSiP2xZkwSmO",
-        "outputId": "41202ce9-f617-4a62-acba-afe99fb40584",
         "colab": {
           "base_uri": "https://localhost:8080/"
-        }
+        },
+        "id": "wSiP2xZkwSmO",
+        "outputId": "41202ce9-f617-4a62-acba-afe99fb40584"
       },
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "\u001b[1m25/25\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 15ms/step\n"
           ]
@@ -1550,15 +1550,14 @@
       "cell_type": "code",
       "execution_count": 20,
       "metadata": {
-        "id": "rSmZGxXDwSmO",
-        "outputId": "647ec968-f97e-4e1b-d041-aea03636b60e",
         "colab": {
           "base_uri": "https://localhost:8080/"
-        }
+        },
+        "id": "rSmZGxXDwSmO",
+        "outputId": "647ec968-f97e-4e1b-d041-aea03636b60e"
       },
       "outputs": [
         {
-          "output_type": "execute_result",
           "data": {
             "text/plain": [
               "array([[18.85141 ],\n",
@@ -1570,8 +1569,9 @@
               "       [17.67097 ]], dtype=float32)"
             ]
           },
+          "execution_count": 20,
           "metadata": {},
-          "execution_count": 20
+          "output_type": "execute_result"
         }
       ],
       "source": [
@@ -1593,34 +1593,21 @@
       "cell_type": "code",
       "execution_count": 21,
       "metadata": {
-        "id": "H_VnZPtDwSmO",
-        "outputId": "c10bf3c1-2781-4bb2-a388-4f859c55e60f",
         "colab": {
           "base_uri": "https://localhost:8080/",
           "height": 455
-        }
+        },
+        "id": "H_VnZPtDwSmO",
+        "outputId": "c10bf3c1-2781-4bb2-a388-4f859c55e60f"
       },
       "outputs": [
         {
-          "output_type": "execute_result",
           "data": {
-            "text/plain": [
+            "application/vnd.google.colaboratory.intrinsic+json": {
-              "            Actual  Predicted\n",
+              "summary": "{\n  \"name\": \"pred_df\",\n  \"rows\": 3139,\n  \"fields\": [\n    {\n      \"column\": \"Date\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"2016-09-29 00:00:00\",\n        \"max\": \"2025-05-03 00:00:00\",\n        \"num_unique_values\": 3139,\n        \"samples\": [\n          \"2021-08-29 00:00:00\",\n          \"2018-12-06 00:00:00\",\n          \"2017-12-23 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Actual\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 4.922379959478632,\n        \"min\": 4.27,\n        \"max\": 23.39,\n        \"num_unique_values\": 1395,\n        \"samples\": [\n          10.32,\n          8.52,\n          15.38\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Predicted\",\n      \"properties\": {\n        \"dtype\": \"float32\",\n        \"num_unique_values\": 3137,\n        \"samples\": [\n          21.144052505493164,\n          8.950167655944824,\n          6.3031134605407715\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
-              "Date                         \n",
+              "type": "dataframe",
-              "2016-09-29   18.54  18.851410\n",
+              "variable_name": "pred_df"
-              "2016-09-30   16.50  18.478785\n",
+            },
-              "2016-10-01   16.03  16.582554\n",
-              "2016-10-02   16.06  16.595911\n",
-              "2016-10-03   17.03  16.462191\n",
-              "...            ...        ...\n",
-              "2025-04-29   16.88  17.737617\n",
-              "2025-04-30   17.44  16.928251\n",
-              "2025-05-01   17.31  17.847725\n",
-              "2025-05-02   17.37  17.350359\n",
-              "2025-05-03   19.26  17.670971\n",
-              "\n",
-              "[3139 rows x 2 columns]"
-            ],
             "text/html": [
               "\n",
               "  <div id=\"df-e72b2590-c412-4153-a00b-da1085937b97\" class=\"colab-df-container\">\n",
@@ -1976,14 +1963,27 @@
               "    </div>\n",
               "  </div>\n"
             ],
-            "application/vnd.google.colaboratory.intrinsic+json": {
+            "text/plain": [
-              "type": "dataframe",
+              "            Actual  Predicted\n",
-              "variable_name": "pred_df",
+              "Date                         \n",
-              "summary": "{\n  \"name\": \"pred_df\",\n  \"rows\": 3139,\n  \"fields\": [\n    {\n      \"column\": \"Date\",\n      \"properties\": {\n        \"dtype\": \"date\",\n        \"min\": \"2016-09-29 00:00:00\",\n        \"max\": \"2025-05-03 00:00:00\",\n        \"num_unique_values\": 3139,\n        \"samples\": [\n          \"2021-08-29 00:00:00\",\n          \"2018-12-06 00:00:00\",\n          \"2017-12-23 00:00:00\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Actual\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 4.922379959478632,\n        \"min\": 4.27,\n        \"max\": 23.39,\n        \"num_unique_values\": 1395,\n        \"samples\": [\n          10.32,\n          8.52,\n          15.38\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Predicted\",\n      \"properties\": {\n        \"dtype\": \"float32\",\n        \"num_unique_values\": 3137,\n        \"samples\": [\n          21.144052505493164,\n          8.950167655944824,\n          6.3031134605407715\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
+              "2016-09-29   18.54  18.851410\n",
-            }
+              "2016-09-30   16.50  18.478785\n",
+              "2016-10-01   16.03  16.582554\n",
+              "2016-10-02   16.06  16.595911\n",
+              "2016-10-03   17.03  16.462191\n",
+              "...            ...        ...\n",
+              "2025-04-29   16.88  17.737617\n",
+              "2025-04-30   17.44  16.928251\n",
+              "2025-05-01   17.31  17.847725\n",
+              "2025-05-02   17.37  17.350359\n",
+              "2025-05-03   19.26  17.670971\n",
+              "\n",
+              "[3139 rows x 2 columns]"
+            ]
           },
+          "execution_count": 21,
           "metadata": {},
-          "execution_count": 21
+          "output_type": "execute_result"
         }
       ],
       "source": [
@@ -2008,16 +2008,16 @@
       "cell_type": "code",
       "execution_count": 22,
       "metadata": {
-        "id": "TA_pBedxwSmT",
-        "outputId": "3da2b6b2-c50c-4656-ffaf-5effd15384d7",
         "colab": {
           "base_uri": "https://localhost:8080/"
-        }
+        },
+        "id": "TA_pBedxwSmT",
+        "outputId": "3da2b6b2-c50c-4656-ffaf-5effd15384d7"
       },
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "0.9214262573889067\n",
             "1.903221483260166\n"
@@ -2034,33 +2034,33 @@
       "cell_type": "code",
       "execution_count": 23,
       "metadata": {
-        "id": "qgPJTuV-wSmT",
-        "outputId": "f7c2277e-be4c-4453-cfc8-651bd08dba4e",
         "colab": {
           "base_uri": "https://localhost:8080/",
           "height": 444
-        }
+        },
+        "id": "qgPJTuV-wSmT",
+        "outputId": "f7c2277e-be4c-4453-cfc8-651bd08dba4e"
       },
       "outputs": [
         {
-          "output_type": "execute_result",
           "data": {
             "text/plain": [
               "<matplotlib.legend.Legend at 0x7c5c445a7cd0>"
             ]
           },
+          "execution_count": 23,
           "metadata": {},
-          "execution_count": 23
+          "output_type": "execute_result"
         },
         {
-          "output_type": "display_data",
           "data": {
+            "image/png": "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 truncated
             "text/plain": [
               "<Figure size 2000x500 with 1 Axes>"
-            ],
+            ]
-            "image/png": "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 truncated
           },
-          "metadata": {}
+          "metadata": {},
+          "output_type": "display_data"
         }
       ],
       "source": [
@@ -2073,9 +2073,10 @@
     }
   ],
   "metadata": {
+    "accelerator": "GPU",
     "colab": {
-      "provenance": [],
+      "gpuType": "T4",
-      "gpuType": "T4"
+      "provenance": []
     },
     "kernelspec": {
       "display_name": "Python 3",
@@ -2092,8 +2093,7 @@
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
       "version": "3.9.18"
-    },
+    }
-    "accelerator": "GPU"
   },
   "nbformat": 4,
   "nbformat_minor": 0

pytorch_port.py

@@ -1,3 +1,5 @@
+import os
+
 from sklearn.model_selection import train_test_split
 import torch
 
@@ -20,23 +22,22 @@ 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 = []
+    xs, ys, dates = [], [], []
-    ys = []
     for i in range(len(data) - seq_length):
-        x = data[i : (i + seq_length)]
+        xs.append(data[i : i + seq_length])
-        y = data[i + seq_length]
+        ys.append(data[i + seq_length])
-        xs.append(x)
+        dates.append(i + seq_length)  # index of target
-        ys.append(y)
+    return np.array(xs), np.array(ys), np.array(dates)
-    return np.array(xs), np.array(ys)
 
 
 seq_length = 20
 
-X, y = create_sequences(scaled_data, seq_length)
+X, y, y_indices = create_sequences(scaled_data, seq_length)
 
 X_train, X_test, y_train, y_test = train_test_split(
     X, y, test_size=0.2, random_state=42
 )
+
 from torch.utils.data import TensorDataset, DataLoader
 
 X_train_tensor = torch.tensor(X_train, dtype=torch.float32)
@@ -66,21 +67,28 @@ class LSTMModel(nn.Module):
         return out
 
 
-model = LSTMModel(
+modfile = "data/model.pth"
+yesmod = os.path.isfile(modfile)
+if yesmod:
+    model = torch.load(modfile)
+else:
+    model = LSTMModel(
         input_size=X_train.shape[2],
         hidden_size=64,
         num_layers=2,
         output_size=y_train.shape[1],
-)
+    )
 model.to(device)
-criterion = nn.MSELoss()
-optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
 
 train_losses = []
 val_losses = []
 
+criterion = nn.MSELoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
 
-for epoch in range(100):
+if not yesmod:
+
+    for epoch in range(100):
         model.train()
         running_train_loss = 0.0
 
@@ -103,6 +111,9 @@ for epoch in range(100):
         epoch_train_loss = running_train_loss / len(train_loader.dataset)
         train_losses.append(epoch_train_loss)
 
+    torch.save(model, modfile)
+    # yesmod = True
+
 model.eval()
 
 X_test_tensor = torch.tensor(X_test, dtype=torch.float32).to(device)
@@ -152,8 +163,17 @@ ax1.legend()
 ax1.grid(True)
 
 # Prediction vs Actual on the right
-ax2.plot(y_test_rescaled, label="Actual")
+
-ax2.plot(predictions_rescaled, label="Predicted")
+# 2024 - 25
+_, X_test_idx, _, y_test_idx = train_test_split(
+    X, y_indices, test_size=0.2, random_state=42
+)
+dates_test = a["Date"].iloc[y_test_idx].values  # Actual datetime values
+
+mask = (dates_test >= "2024-01-01") & (dates_test <= "2025-12-31")
+# Plot the results
+ax2.plot(dates_test[mask], y_test_rescaled[mask], label="Actual")
+ax2.plot(dates_test[mask], predictions_rescaled[mask], label="Predicted")
 ax2.set_title("Actual vs. Predicted")
 ax2.set_xlabel("Sample")
 ax2.set_ylabel("Value")

sklearn_port.py

@@ -1,85 +0,0 @@
-import sys
-import numpy as np
-import pandas as pd
-from sklearn.metrics import r2_score
-from sklearn.preprocessing import MinMaxScaler
-from sklearn.model_selection import train_test_split
-from sklearn.ensemble import RandomForestRegressor
-from sklearn.metrics import mean_squared_error
-import matplotlib.pyplot as plt
-from global_config import DATA_FILE_NAME
-from load_data import cut_headers
-
-# 1. Load data
-
-with open(DATA_FILE_NAME, "r", encoding="utf-8") as file:
-    data_header, csv_file = cut_headers(file)
-    data = pd.read_csv(csv_file, na_values=-999)
-
-if all(z in data.columns for z in ("YEAR", "MO", "DY")):
-    data["date"] = pd.to_datetime(
-        {k: data[v] for v, k in (zip(["YEAR", "MO", "DY"], ["year", "month", "day"]))}
-    )
-    data.drop(inplace=True, columns=["YEAR", "MO", "DY"])
-    data.set_index(["date"], inplace=True)
-data.dropna(inplace=True)
-
-# 2. Normalize data
-scaler = MinMaxScaler()
-print(data.columns)
-scaled_data = scaler.fit_transform(data)
-
-
-# 3. Create sequences for supervised learning
-def create_sequences(data, seq_length):
-    xs, ys = [], []
-    for i in range(len(data) - seq_length):
-        x = data[i : i + seq_length].flatten()
-        y = data[i + seq_length]
-        xs.append(x)
-        ys.append(y)
-    return np.array(xs), np.array(ys)
-
-
-seq_length = 50
-X, y = create_sequences(scaled_data, seq_length)
-
-# 4. Split into training and testing
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.02, shuffle=False)
-
-# 5. Train linear regression model
-model = RandomForestRegressor(
-        n_estimators=200,       # Number of trees
-        # max_features='sqrt',    # Features considered at each split
-        # max_depth=30,           # Maximum depth of each tree
-        # n_jobs=-1,              # Use all CPU cores
-        random_state=42         # Reproducibility
-)
-model.fit(X_train, y_train)
-
-# 6. Make predictions
-predictions = model.predict(X_test)
-
-# 7. Evaluate performance
-mse = mean_squared_error(y_test, predictions)
-r2 = r2_score(y_test, predictions)
-
-print(f"Test MSE: {mse:.4f}")
-print(f"Test r2: {r2:.4f}")
-
-print(f"Score: {model.score(X_test, y_test)}")
-# 8. Inverse transform predictions
-predictions_rescaled = scaler.inverse_transform(predictions.reshape(-1, data.shape[1]))
-y_test_rescaled = scaler.inverse_transform(y_test.reshape(-1, data.shape[1]))
-
-# 9. Plot results
-for i, column in enumerate(data.columns):
-    plt.figure(figsize=(10, 5))
-    plt.plot(y_test_rescaled[:, i], label=f"Actual {column}")
-    plt.plot(predictions_rescaled[:, i], label=f"Predicted {column}")
-    plt.title(f"Actual vs. Predicted for {column}")
-    plt.xlabel("Sample")
-    plt.ylabel("Value")
-    plt.legend()
-    plt.tight_layout()
-    plt.show()