Spaces:
Sleeping
Sleeping
Shafeek Saleem
commited on
Commit
·
66b198b
1
Parent(s):
bbdc057
ss
Browse files
pages/3_Training the Model.py
CHANGED
@@ -55,6 +55,10 @@ def create_model_inputs(data, lag, mean_period, target_variable):
|
|
55 |
["Location", "MinTemp", "MaxTemp", "Rainfall", "WindGustDir", "WindGustSpeed", "WindDir9am", "WindDir3pm",
|
56 |
"WindSpeed9am", "WindSpeed3pm", "Humidity9am", "Humidity3pm", "Pressure9am", "Pressure3pm", "Temp9am",
|
57 |
"Temp3pm", "RainToday", target_variable + "_mean"]]
|
|
|
|
|
|
|
|
|
58 |
X = pd.get_dummies(X, columns=['Location', 'WindGustDir', 'WindDir9am', 'WindDir3pm'])
|
59 |
y = df_processed[target_variable + "Tomorrow"].loc[X.index]
|
60 |
|
@@ -161,13 +165,12 @@ def step3_page():
|
|
161 |
st.subheader("Step 2: Data Preprocessing and Feature Engineering")
|
162 |
st.write("Now let's preprocess our dataset to handle missing values, outliers and inconsistencies and then perform feature engineering tasks to extract meaningful features from the raw data. Finally we need to separate training variables (X) and target variable (y).")
|
163 |
st.info("You can select the weather attribute that you want to forecast (WindSpeed/ Humidity/ Pressure/ Temperature) and the time of the forecast (9am tomorrow/ 3pm tomorrow)")
|
164 |
-
|
165 |
-
|
166 |
-
|
167 |
-
|
168 |
-
|
169 |
-
|
170 |
-
time = st.selectbox('Select the Time of the Forecast for Tomorrow', times)
|
171 |
target_variable = attribute+time
|
172 |
X, y, target_variable_name = create_model_inputs(data, 1, 30, target_variable)
|
173 |
cols = st.columns(2)
|
|
|
55 |
["Location", "MinTemp", "MaxTemp", "Rainfall", "WindGustDir", "WindGustSpeed", "WindDir9am", "WindDir3pm",
|
56 |
"WindSpeed9am", "WindSpeed3pm", "Humidity9am", "Humidity3pm", "Pressure9am", "Pressure3pm", "Temp9am",
|
57 |
"Temp3pm", "RainToday", target_variable + "_mean"]]
|
58 |
+
from sklearn.preprocessing import LabelEncoder
|
59 |
+
label_encoder = LabelEncoder()
|
60 |
+
X['RainToday'] = label_encoder.fit_transform(X['RainToday'])
|
61 |
+
|
62 |
X = pd.get_dummies(X, columns=['Location', 'WindGustDir', 'WindDir9am', 'WindDir3pm'])
|
63 |
y = df_processed[target_variable + "Tomorrow"].loc[X.index]
|
64 |
|
|
|
165 |
st.subheader("Step 2: Data Preprocessing and Feature Engineering")
|
166 |
st.write("Now let's preprocess our dataset to handle missing values, outliers and inconsistencies and then perform feature engineering tasks to extract meaningful features from the raw data. Finally we need to separate training variables (X) and target variable (y).")
|
167 |
st.info("You can select the weather attribute that you want to forecast (WindSpeed/ Humidity/ Pressure/ Temperature) and the time of the forecast (9am tomorrow/ 3pm tomorrow)")
|
168 |
+
|
169 |
+
attributes = ['WindSpeed', 'Humidity', 'Pressure', 'Temp']
|
170 |
+
attribute = st.selectbox('Select the Weather Attribute', attributes)
|
171 |
+
|
172 |
+
times = ['9am', '3pm']
|
173 |
+
time = st.selectbox('Select the Time of the Forecast for Tomorrow', times)
|
|
|
174 |
target_variable = attribute+time
|
175 |
X, y, target_variable_name = create_model_inputs(data, 1, 30, target_variable)
|
176 |
cols = st.columns(2)
|