import numpy as np import pandas as pd from sklearn.linearmodel import LinearRegression…
- User
import numpy as np import pandas as pd from sklearn.linear_model import LinearRegression from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score from sklearn.model_selection import train_test_split, cross_val_score from sklearn.model_selection import GridSearchCV
Load the dataset
data = pd.read_excel(‘Data20231118.xlsx’, index_col=0, sheet_name='value')
#check statistical aspects of the dataframe data.describe()
#check the type of each column data.info()
#check column name data.columns()
Split the data into predictor variables (X) and target variable (y)
X = data[[‘Week’, ‘Temperature’, ‘Humidity’, ‘Rainfall’, ‘AirIndex’]] y = data['Adm_0_5','Adm_6_11','Adm_12_17','Adm_18_49','Adm_50_64','Adm_65_higher']
Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
Create a Linear Regression model
model = LinearRegression()
Train the model on the training data
model.fit(X_train, y_train)
Make predictions on the test data
y_pred = model.predict(X_test)
Evaluation metrics
mse = mean_squared_error(y_test, y_pred) rmse = np.sqrt(mse) mae = mean_absolute_error(y_test, y_pred) r2 = r2_score(y_test, y_pred)
print(“Mean Squared Error (MSE):”, mse) print(“Root Mean Squared Error (RMSE):”, rmse) print(“Mean Absolute Error (MAE):”, mae) print(“R-squared:”, r2)
Hyperparameter Tuning using cross-validation
params = {‘fit_intercept’: [True, False], ‘normalize’: [True, False], ‘copy_X’: [True, False]}
grid_search = GridSearchCV(model, params, cv=5) grid_search.fit(X_train, y_train)
best_params = grid_search.best_params_ best_score = grid_search.best_score_
print(“Best Parameters:”, best_params) print(“Best Score (R-squared):”, best_score)
here is the python code, the objective is predict multiple y. please review entire code, and check the code of "y = data['Adm_0_5','Adm_6_11','Adm_12_17','Adm_18_49','Adm_50_64','Adm_65_higher']". please modify entire code, the objective is provide multiple regression and predict multiple y
- Assistant
Sure, I can help you modify the code to provide multiple regression and predict multiple y. Here's the modified code:
import numpy as np import pandas as pd from sklearn.linear_model import LinearRegression from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score from sklearn.model_selection import train_test_split, cross_val_score from sklearn.model_selection import GridSearchCV # Load the dataset data = pd.read_excel('Data20231118.xlsx', index_col=0, sheet_name='value') # Check statistical aspects of the dataframe data.describe() # Check the type of each column data.info() # Check column names data.columns # Split the data into predictor variables (X) and target variables (y) X = data[['Week', 'Temperature', 'Humidity', 'Rainfall', 'AirIndex']] y = data[['Adm_0_5','Adm_6_11','Adm_12_17','Adm_18_49','Adm_50_64','Adm_65_higher']] # Split the data into training and testing sets X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) # Create a Linear Regression model for each target variable models = {} y_preds = {} mse = {} rmse = {} mae = {} r2 = {} for column in y.columns: model = LinearRegression() model.fit(X_train, y_train[column]) models[column] = model y_pred = model.predict(X_test) y_preds[column] = y_pred mse[column] = mean_squared_error(y_test[column], y_pred) rmse[column] = np.sqrt(mse[column]) mae[column] = mean_absolute_error(y_test[column], y_pred) r2[column] = r2_score(y_test[column], y_pred) # Print evaluation metrics for each target variable for column in y.columns: print("Evaluation metrics for", column) print("Mean Squared Error (MSE):", mse[column]) print("Root Mean Squared Error (RMSE):", rmse[column]) print("Mean Absolute Error (MAE):", mae[column]) print("R-squared:", r2[column]) print() # Hyperparameter Tuning using cross-validation params = {'fit_intercept': [True, False], 'normalize': [True, False], 'copy_X': [True, False]} best_params = {} best_score = {} for column in y.columns: grid_search = GridSearchCV(models[column], params, cv=5) grid_search.fit(X_train, y_train[column]) best_params[column] = grid_search.best_params_ best_score[column] = grid_search.best_score_ # Print best parameters and score for each target variable for column in y.columns: print("Best Parameters for", column) print("Best Parameters:", best_params[column]) print("Best Score (R-squared):", best_score[column]) print()In this modified code, I added a loop to create multiple linear regression models for each target variable in
y. The loop also calculates the evaluation metrics for each target variable separately. Additionally, I added another loop for hyperparameter tuning using cross-validation for each target variable. Finally, I print the evaluation metrics and best parameters/scores for each target variable separately. - User
here is the error message
KeyError Traceback (most recent call last) Cell In[5], line 21 18 data.columns 20 # Split the data into predictor variables (X) and target variables (y) ---> 21 X = data[['Week', 'Temperature', 'Humidity', 'Rainfall', 'AirIndex']] 22 y = data[['Adm_0_5','Adm_6_11','Adm_12_17','Adm_18_49','Adm_50_64','Adm_65_higher']] 24 # Split the data into training and testing sets
File ~\AppData\Local\anaconda3\Lib\site-packages\pandas\core\frame.py:3767, in DataFrame.getitem(self, key) 3765 if is_iterator(key): 3766 key = list(key) -> 3767 indexer = self.columns._get_indexer_strict(key, "columns")[1] 3769 # take() does not accept boolean indexers 3770 if getattr(indexer, "dtype", None) == bool:
File ~\AppData\Local\anaconda3\Lib\site-packages\pandas\core\indexes\base.py:5877, in Index._get_indexer_strict(self, key, axis_name) 5874 else: 5875 keyarr, indexer, new_indexer = self._reindex_non_unique(keyarr) -> 5877 self._raise_if_missing(keyarr, indexer, axis_name) 5879 keyarr = self.take(indexer) 5880 if isinstance(key, Index): 5881 # GH 42790 - Preserve name from an Index
File ~\AppData\Local\anaconda3\Lib\site-packages\pandas\core\indexes\base.py:5941, in Index._raise_if_missing(self, key, indexer, axis_name) 5938 raise KeyError(f"None of [{key}] are in the [{axis_name}]") 5940 not_found = list(ensure_index(key)[missing_mask.nonzero()[0]].unique()) -> 5941 raise KeyError(f"{not_found} not in index")
KeyError: "['Humidity'] not in index"
- Assistant
The error message suggests that the column name 'Humidity' is not present in the index of the DataFrame.
To resolve this issue, you can try the following steps:
-
Check if the column name 'Humidity' is spelled correctly in the dataset. Check for any leading or trailing whitespaces in the column name as well.
-
Verify the index of the DataFrame by printing
data.indexand ensure that it contains the expected values. If the index does not match your expectations, you may need to specify the correct index column when reading the Excel file using theindex_colparameter inpd.read_excel(). -
If the column name exists in the dataset but is not present in the index, you can access it using
data['Humidity']instead ofdata[['Week', 'Temperature', 'Humidity', 'Rainfall', 'AirIndex']].
Additionally, make sure all the other column names specified in the code are present in the dataset and their names are spelled correctly. Double-check all the column names to ensure they match the actual column names in your dataset.
-