Spaces:
Runtime error
Runtime error
| #%% | |
| from matplotlib.pyplot import title | |
| import tensorflow as tf | |
| from tensorflow import keras | |
| from huggingface_hub import from_pretrained_keras | |
| import pandas as pd | |
| import matplotlib.pyplot as plt | |
| import streamlit as st | |
| from zipfile import ZipFile | |
| import os | |
| if ("0" != "mycustom"): | |
| import datetime | |
| from io import StringIO | |
| import warnings | |
| warnings.filterwarnings("ignore") | |
| if ("0" == "mycustom"): | |
| os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID" | |
| os.environ["CUDA_VISIBLE_DEVICES"] = "" | |
| if ("0" == "mycustom"): | |
| 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) | |
| if ("0" == "mycustom"): | |
| mybacklogmax = 10000 | |
| df = df.head(n=mybacklogmax) | |
| st.dataframe(df) | |
| if ("0" != "mycustom"): | |
| myfields = [0, 1, 5, 7, 8, 10, 11] | |
| myfields = [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)"] | |
| mybacklogmax = 10 | |
| atoday = datetime.date.today() | |
| ayear = int(atoday.strftime("%Y"))-0 | |
| amonth = int(atoday.strftime("%m")) | |
| amonthday = int(atoday.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) | |
| #%% | |
| title = "Timeseries forecasting for weather prediction" | |
| st.title('Timeseries forecasting for weather prediction') | |
| st.write("Demonstrates how to do timeseries forecasting using a [LSTM model.](https://keras.io/api/layers/recurrent_layers/lstm/#lstm-class)This space demonstration is forecasting for weather prediction. *n* observation is selected from validation dataset." ) | |
| st.write("Keras example authors: [Prabhanshu Attri, Yashika Sharma, Kristi Takach, Falak Shah](https://keras.io/examples/timeseries/timeseries_weather_forecasting/)") | |
| # %% model | |
| titles = [ | |
| "Pressure", | |
| "Temperature", | |
| "Temperature in Kelvin", | |
| "Temperature (dew point)", | |
| "Relative Humidity", | |
| "Saturation vapor pressure", | |
| "Vapor pressure", | |
| "Vapor pressure deficit", | |
| "Specific humidity", | |
| "Water vapor concentration", | |
| "Airtight", | |
| "Wind speed", | |
| "Maximum wind speed", | |
| "Wind direction in degrees", | |
| ] | |
| feature_keys = [ | |
| "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)", | |
| ] | |
| date_time_key = "Date Time" | |
| split_fraction = 0.715 | |
| train_split = int(split_fraction * int(df.shape[0])) | |
| step = 6 | |
| past = 720 | |
| future = 72 | |
| learning_rate = 0.001 | |
| batch_size = 256 | |
| epochs = 10 | |
| if ("0" != "mycustom"): | |
| past = 0 | |
| future = 1 | |
| batch_size = 1 | |
| step = 1 | |
| def normalize(data, train_split): | |
| data_mean = data[:train_split].mean(axis=0) | |
| data_std = data[:train_split].std(axis=0) | |
| return (data - data_mean) / data_std | |
| print( | |
| "The selected parameters are:", | |
| ", ".join([titles[i] for i in [0, 1, 5, 7, 8, 10, 11]]), | |
| ) | |
| selected_features = [feature_keys[i] for i in [0, 1, 5, 7, 8, 10, 11]] | |
| if ("0" != "mycustom"): | |
| print( | |
| "The selected parameters are:", | |
| ", ".join([titles[i] for i in myfields]), | |
| ) | |
| selected_features = [feature_keys[i] for i in myfields] | |
| features = df[selected_features] | |
| features.index = df[date_time_key] | |
| features.head() | |
| features = normalize(features.values, train_split) | |
| features = pd.DataFrame(features) | |
| features.head() | |
| train_data = features.loc[0 : train_split - 1] | |
| val_data = features.loc[train_split:] | |
| split_fraction = 0.715 | |
| train_split = int(split_fraction * int(df.shape[0])) | |
| step = 6 | |
| past = 720 | |
| future = 72 | |
| learning_rate = 0.001 | |
| batch_size = 256 | |
| epochs = 10 | |
| if ("0" != "mycustom"): | |
| past = 0 | |
| future = 1 | |
| batch_size = 1 | |
| step = 1 | |
| def normalize(data, train_split): | |
| data_mean = data[:train_split].mean(axis=0) | |
| data_std = data[:train_split].std(axis=0) | |
| return (data - data_mean) / data_std | |
| print( | |
| "The selected parameters are:", | |
| ", ".join([titles[i] for i in [0, 1, 5, 7, 8, 10, 11]]), | |
| ) | |
| selected_features = [feature_keys[i] for i in [0, 1, 5, 7, 8, 10, 11]] | |
| if ("0" != "mycustom"): | |
| print( | |
| "The selected parameters are:", | |
| ", ".join([titles[i] for i in myfields]), | |
| ) | |
| selected_features = [feature_keys[i] for i in myfields] | |
| features = df[selected_features] | |
| features.index = df[date_time_key] | |
| features.head() | |
| features = normalize(features.values, train_split) | |
| features = pd.DataFrame(features) | |
| features.head() | |
| train_data = features.loc[0 : train_split - 1] | |
| val_data = features.loc[train_split:] | |
| start = past + future | |
| end = start + train_split | |
| if ("0" == "mycustom"): | |
| x_train = train_data[[i for i in range(7)]].values | |
| y_train = features.iloc[start:end][[1]] | |
| if ("0" != "mycustom"): | |
| x_train = train_data[[i for i in range(len(myfields))]].values | |
| y_train = features.iloc[start:end][[0]] | |
| sequence_length = int(past / step) | |
| x_end = len(val_data) - past - future | |
| label_start = train_split + past + future | |
| st.write(label_start) | |
| if ("0" == "mycustom"): | |
| x_val = val_data.iloc[:x_end][[i for i in range(7)]].values | |
| y_val = features.iloc[label_start:][[1]] | |
| if ("0" != "mycustom"): | |
| x_val = val_data.iloc[:x_end][[i for i in range(len(myfields))]].values | |
| y_val = features.iloc[label_start:][[0]] | |
| dataset_val = keras.preprocessing.timeseries_dataset_from_array( | |
| x_val, | |
| y_val, | |
| sequence_length=sequence_length, | |
| sampling_rate=step, | |
| batch_size=batch_size, | |
| ) | |
| #%% | |
| model = from_pretrained_keras("keras-io/timeseries_forecasting_for_weather") | |
| #%% | |
| st.set_option('deprecation.showPyplotGlobalUse', False) | |
| def plot(): | |
| n = st.sidebar.slider("Step", min_value = 1, max_value=5, value = 1) | |
| def show_plot(plot_data, delta, title): | |
| labels = ["History", "True Future", "Model Prediction"] | |
| marker = [".-", "rx", "go"] | |
| time_steps = list(range(-(plot_data[0].shape[0]), 0)) | |
| if delta: | |
| future = delta | |
| else: | |
| future = 0 | |
| plt.title(title) | |
| for i, val in enumerate(plot_data): | |
| if i: | |
| plt.plot(future, plot_data[i], marker[i], markersize=10, label=labels[i]) | |
| else: | |
| plt.plot(time_steps, plot_data[i].flatten(), marker[i], label=labels[i]) | |
| plt.legend(loc='lower center', bbox_to_anchor=(0.5, 1.05), | |
| ncol=3, fancybox=True, shadow=True) | |
| plt.xlim([time_steps[0], (future + 5) * 2]) | |
| plt.xlabel("Time-Step") | |
| plt.show() | |
| return | |
| for x, y in dataset_val.take(n): | |
| if ("0" == "mycustom"): | |
| show_plot( | |
| [x[0][:, 1].numpy(), y[0].numpy(), model.predict(x)[0]], | |
| 12, | |
| f"{n} Step Prediction", | |
| ) | |
| if ("0" != "mycustom"): | |
| show_plot( | |
| [x[0][:, 0].numpy(), y[0].numpy(), model.predict(x)[0]], | |
| 12, | |
| f"{n} Step Prediction", | |
| ) | |
| fig = plot() | |
| st.pyplot(fig) | |
| # %% | |