Update app.py

app.py

@@ -1,4 +1,3 @@
-
 #%%
 from matplotlib.pyplot import title
 import tensorflow as tf
@@ -9,57 +8,20 @@ import matplotlib.pyplot as plt
 import streamlit as st
 from zipfile import ZipFile
 import os
-import datetime
-from io import StringIO
 
 import warnings
 warnings.filterwarnings("ignore")
 
-#
-mylist = [0, 1, 5, 7, 8, 10, 11]
-mylist = [1]
-mytitles = ["Date Time","p (mbar)","T (degC)","Tpot (K)","Tdew (degC)","rh (%)","VPmax (mbar)","VPact (mbar)","VPdef (mbar)","sh (g/kg)","H2OC (mmol/mol)","rho (g/m**3)","wv (m/s)","max. wv (m/s)","wd (deg)"]
-df = pd.DataFrame(columns=mytitles)
-os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"   # see issue #152
-os.environ["CUDA_VISIBLE_DEVICES"] = ""
-mybacklogmax = 5
-
-if ("0" == ""):
-	uri = "https://storage.googleapis.com/tensorflow/tf-keras-datasets/jena_climate_2009_2016.csv.zip"
-	zip_path = keras.utils.get_file(origin=uri, fname="jena_climate_2009_2016.csv.zip")
-	zip_file = ZipFile(zip_path)
-	zip_file.extractall()
-	csv_path = "jena_climate_2009_2016.csv"
-	df = pd.read_csv(csv_path)
-	st.dataframe(df)
-
-if ("0" != ""):
-	today = datetime.date.today()
-
-	ayear = int(today.strftime("%Y"))-0
-	amonth = int(today.strftime("%m"))
-	amonthday = int(today.strftime("%d"))
-
-	csvString = ""
-	csvString += (",").join(mytitles)
-	adf = pd.DataFrame(columns=mytitles)
-	for i in range((ayear-mybacklogmax),ayear,1):
-		alink = ("https://data.weather.gov.hk/weatherAPI/opendata/opendata.php?dataType=CLMTEMP&year={}&rformat=csv&station=HKO").format(str(i))
-		df = pd.read_csv(alink, skiprows=[0,1,2], skipfooter=3, engine='python', on_bad_lines='skip')
-
-		df = df.reset_index()  # make sure indexes pair with number of rows
-		for index, row in df.iterrows():
-			if (row[2]!=amonth) or (row[3]!=amonthday):
-				continue
-
-			adate = ("{:02d}.{:02d}.{} 00:00:00").format(row[3], row[2], row[1])
-			csvString += '\n'+(",").join([adate,"",str(row[4]),"","","","","","","","","","","",""])
-			st.write(row[0],adate)
-			adf = adf.append({"Date Time":adate,"T (degC)":(row[4]),}, ignore_index=True)
-			break
-	adf = pd.read_csv(StringIO(csvString), sep=",")
-	df = adf
-	st.dataframe(df)
+if ("0" == "mycustom"):
+	os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
+	os.environ["CUDA_VISIBLE_DEVICES"] = ""
+
+uri = "https://storage.googleapis.com/tensorflow/tf-keras-datasets/jena_climate_2009_2016.csv.zip"
+zip_path = keras.utils.get_file(origin=uri, fname="jena_climate_2009_2016.csv.zip")
+zip_file = ZipFile(zip_path)
+zip_file.extractall()
+csv_path = "jena_climate_2009_2016.csv"
+df = pd.read_csv(csv_path)
 
 #%%
 
@@ -127,9 +89,9 @@ def normalize(data, train_split):
 
 print(
     "The selected parameters are:",
-    ", ".join([titles[i] for i in mylist]),
+    ", ".join([titles[i] for i in [0, 1, 5, 7, 8, 10, 11]]),
 )
-selected_features = [feature_keys[i] for i in mylist]
+selected_features = [feature_keys[i] for i in [0, 1, 5, 7, 8, 10, 11]]
 features = df[selected_features]
 features.index = df[date_time_key]
 features.head()
@@ -159,9 +121,9 @@ def normalize(data, train_split):
     return (data - data_mean) / data_std
 print(
     "The selected parameters are:",
-    ", ".join([titles[i] for i in mylist]),
+    ", ".join([titles[i] for i in [0, 1, 5, 7, 8, 10, 11]]),
 )
-selected_features = [feature_keys[i] for i in mylist]
+selected_features = [feature_keys[i] for i in [0, 1, 5, 7, 8, 10, 11]]
 features = df[selected_features]
 features.index = df[date_time_key]
 features.head()
@@ -175,48 +137,16 @@ val_data = features.loc[train_split:]
 start = past + future
 end = start + train_split
 
-st.dataframe(features)
-st.dataframe(train_data)
-st.dataframe(val_data)
-
-myrangeend = int(split_fraction*mybacklogmax)
-#mycolumns = df[date_time_key]
-mycolumns = pd.RangeIndex(0, myrangeend).to_series()
-#train_data = train_data.reindex(columns=mycolumns)
-
-st.write(val_data.to_numpy())
-
-#x_train = train_data[[i for i in range(myrangeend)]].values
-x_train = train_data.to_numpy()
-#y_train = features.iloc[start:end][[1]]
-#y_train = features.reindex(columns=mycolumns).iloc[start:end][[1]]
-
-
-y_train = df[date_time_key].loc[0 : train_split - 1].to_numpy()
-
-st.write(x_train)
-st.write(y_train)
-
+x_train = train_data[[i for i in range(7)]].values
+y_train = features.iloc[start:end][[1]]
 
 sequence_length = int(past / step)
 x_end = len(val_data) - past - future
 
 label_start = train_split + past + future
 
-#x_val = val_data.iloc[:x_end][[i for i in range(myrangeend)]].values
-#y_val = features.iloc[label_start:][[1]]
-
-x_val = val_data.iloc[:x_end].to_numpy()
-y_val = df[date_time_key].iloc[label_start:].to_numpy()
-
-#x_val = val_data.reindex(columns=mycolumns)
-#x_val = x_val.iloc[:x_end][[i for i in range(myrangeend)]].values
-#y_val = features.reindex(columns=mycolumns)
-#y_val = y_val.iloc[label_start:][[1]]
-
-st.write(x_val,x_end)
-st.write(y_val,label_start)
-
+x_val = val_data.iloc[:x_end][[i for i in range(7)]].values
+y_val = features.iloc[label_start:][[1]]
 
 dataset_val = keras.preprocessing.timeseries_dataset_from_array(
     x_val,
@@ -266,4 +196,3 @@ fig = plot()
 st.pyplot(fig)
 
 # %%
-