Spaces:
Runtime error
Runtime error
File size: 5,201 Bytes
d4e742a 6d22a12 ae1d4ed 6d22a12 d4e742a da8babf d4e742a df42c7c d4e742a 2cc6c6f d4e742a 6d22a12 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 |
#%%
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
import warnings
warnings.filterwarnings("ignore")
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)
#%%
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
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]]
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
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]]
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
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(7)]].values
y_val = features.iloc[label_start:][[1]]
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):
show_plot(
[x[0][:, 1].numpy(), y[0].numpy(), model.predict(x)[0]],
12,
f"{n} Step Prediction",
)
fig = plot()
st.pyplot(fig)
# %% |