-
-
Save preetesh33/dafe683408d67d2fd3d78a243bb87c67 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import pandas as pd | |
from joblib import load | |
import json | |
from datetime import datetime | |
import warnings | |
warnings.filterwarnings("ignore", category=FutureWarning) | |
warnings.filterwarnings("ignore", category=DeprecationWarning) | |
warnings.filterwarnings("ignore", message="Found null values in totalcalls.") | |
start_time = '2024-02-16' | |
end_time = '2024-02-17' | |
location_json = 'location_mapping.json' | |
customer_json = 'customer_mapping.json' | |
cluster_json = 'cluster_mapping.json' | |
project_json = 'project_mapping.json' | |
df_grouped = pd.read_csv('/opt/ML/final/data_augmentation/augmentation/merged_main.csv') | |
# Convert 'timestamp' to datetime | |
df_grouped['timestamp'] = pd.to_datetime(df_grouped['timestamp']) | |
# Convert object columns to category type | |
df_grouped['location'] = df_grouped['location'].astype('category') | |
df_grouped['customer'] = df_grouped['customer'].astype('category') | |
df_grouped['cluster'] = df_grouped['cluster'].astype('category') | |
df_grouped['project'] = df_grouped['project'].astype('category') | |
# Create a mapping of codes to labels for each category column dictionary | |
location_mapping_dict = dict(enumerate(df_grouped['location'].cat.categories)) | |
customer_mapping_dict = dict(enumerate(df_grouped['customer'].cat.categories)) | |
cluster_mapping_dict = dict(enumerate(df_grouped['cluster'].cat.categories)) | |
project_mapping_dict = dict(enumerate(df_grouped['project'].cat.categories)) | |
# Convert category columns to integer encoding | |
df_grouped['location'] = df_grouped['location'].cat.codes | |
df_grouped['customer'] = df_grouped['customer'].cat.codes | |
df_grouped['cluster'] = df_grouped['cluster'].cat.codes | |
df_grouped['project'] = df_grouped['project'].cat.codes | |
# two days data | |
#df_grouped = df_grouped[(df_grouped['timestamp'] >= start_time) & (df_grouped['timestamp'] <= end_time)] | |
df_grouped = df_grouped[(df_grouped['timestamp'] > start_time) & (df_grouped['timestamp'] < end_time)] | |
print("train head",df_grouped.head(10)) | |
print("train tail",df_grouped.tail(10)) | |
_horizon = len(df_grouped) | |
df_grouped['id_col'] = df_grouped['location'].astype(str) + '_' + df_grouped['customer'].astype(str) + '_' + df_grouped['cluster'].astype(str) + '_' + df_grouped['project'].astype(str) | |
# Load the model | |
model = load('test_train_1.joblib') | |
# Make predictions | |
pred = model.predict(horizon=1440,dynamic_dfs=[df_grouped], ids=df_grouped.id_col.unique().tolist()) | |
# Splitting the numbers and creating two separate columns | |
pred[['location', 'customer', 'cluster', 'project']] = pred['id_col'].str.split('_', expand=True) | |
print("prediction head",pred.head(10)) | |
# load json files | |
location_mapping_json = json.load(open(location_json)) | |
customer_mapping_json = json.load(open(customer_json)) | |
cluster_mapping_json = json.load(open(cluster_json)) | |
project_mapping_json = json.load(open(project_json)) | |
# Convert the keys back to integers | |
location_mapping_json = {int(k): v for k, v in location_mapping_json.items()} | |
customer_mapping_json = {int(k): v for k, v in customer_mapping_json.items()} | |
cluster_mapping_json = {int(k): v for k, v in cluster_mapping_json.items()} | |
project_mapping_json = {int(k): v for k, v in project_mapping_json.items()} | |
# Convert 'cat1' and 'customer' to integers | |
pred['location'] = pred['location'].astype(int) | |
pred['customer'] = pred['customer'].astype(int) | |
pred['cluster'] = pred['cluster'].astype(int) | |
pred['project'] = pred['project'].astype(int) | |
# Now, to convert back to original categories | |
pred['location'] = pred['location'].map(location_mapping_json) | |
pred['customer'] = pred['customer'].map(customer_mapping_json) | |
pred['cluster'] = pred['cluster'].map(cluster_mapping_json) | |
pred['project'] = pred['project'].map(project_mapping_json) | |
print("final pred data",pred.head(10)) | |
pred.to_csv('test_pred_1,csv', index=False) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment