chore: run hatch fmt to format to 120 width

Signed-off-by: Sunil Thaha <[email protected]>

Author: Sunil Thaha

cmd/main.py

@@ -3,6 +3,7 @@
 # -*- coding: utf-8 -*-
 import re
 import sys
+
 from kepler_model.cmd.main import run
 
 if __name__ == "__main__":

model_training/s3/src/s3/loader.py

@@ -4,6 +4,7 @@
 # <provider>_upload(client, mnt_path)
 import argparse
 import os
+
 from . import util
 
 model_dir = "models"

model_training/s3/src/s3/pusher.py

@@ -2,8 +2,9 @@
 # client = new_<provider>_client(args)
 ## upload all files in mnt path
 # <provider>_upload(client, mnt_path)
-import os
 import argparse
+import os
+
 from . import util
 
 model_dir = "models"

model_training/s3/src/s3/util.py

@@ -1,4 +1,5 @@
 import argparse
+
 import s3.__about__ as about
 
 

src/kepler_model/cmd/cmd_plot.py

@@ -1,11 +1,11 @@
 import os
-from kepler_model.util.prom_types import TIMESTAMP_COL
-from kepler_model.util import PowerSourceMap
 
-from kepler_model.util.train_types import FeatureGroup, ModelOutputType, weight_support_trainers
-from kepler_model.util.loader import load_metadata, load_scaler, get_model_group_path
-from kepler_model.train.profiler.node_type_index import NodeTypeIndexCollection
 from kepler_model.estimate import load_model
+from kepler_model.train.profiler.node_type_index import NodeTypeIndexCollection
+from kepler_model.util import PowerSourceMap
+from kepler_model.util.loader import get_model_group_path, load_metadata, load_scaler
+from kepler_model.util.prom_types import TIMESTAMP_COL
+from kepler_model.util.train_types import FeatureGroup, ModelOutputType, weight_support_trainers
 
 markers = ["o", "s", "^", "v", "<", ">", "p", "P", "*", "x", "+", "|", "_"]
 
@@ -18,14 +18,14 @@ def ts_plot(data, cols, title, output_folder, name, labels=None, subtitles=None,
 
     sns.set(font_scale=1.2)
     fig, axes = plt.subplots(len(cols), 1, figsize=(plot_width, len(cols) * plot_height))
-    for i in range(0, len(cols)):
+    for i in range(len(cols)):
         if len(cols) == 1:
             ax = axes
         else:
             ax = axes[i]
         if isinstance(cols[i], list):
             # multiple lines
-            for j in range(0, len(cols[i])):
+            for j in range(len(cols[i])):
                 sns.lineplot(data=data, x=TIMESTAMP_COL, y=cols[i][j], ax=ax, label=labels[j])
             ax.set_title(subtitles[i])
         else:
@@ -52,27 +52,26 @@ def feature_power_plot(data, model_id, output_type, energy_source, feature_cols,
     col_num = len(actual_power_cols)
     width = max(10, col_num * plot_width)
     fig, axes = plt.subplots(row_num, col_num, figsize=(width, row_num * plot_height))
-    for xi in range(0, row_num):
+    for xi in range(row_num):
         feature_col = feature_cols[xi]
-        for yi in range(0, col_num):
+        for yi in range(col_num):
             if row_num == 1:
                 if col_num == 1:
                     ax = axes
                 else:
                     ax = axes[yi]
+            elif col_num == 1:
+                ax = axes[xi]
             else:
-                if col_num == 1:
-                    ax = axes[xi]
-                else:
-                    ax = axes[xi][yi]
+                ax = axes[xi][yi]
             sorted_data = data.sort_values(by=[feature_col])
             sns.scatterplot(data=sorted_data, x=feature_col, y=actual_power_cols[yi], ax=ax, label="actual")
             sns.lineplot(data=sorted_data, x=feature_col, y=predicted_power_cols[yi], ax=ax, label="predicted", color="C1")
             if xi == 0:
                 ax.set_title(actual_power_cols[yi])
             if yi == 0:
                 ax.set_ylabel("Power (W)")
-    title = "{} {} prediction correlation \n by {}".format(energy_source, output_type, model_id)
+    title = f"{energy_source} {output_type} prediction correlation \n by {model_id}"
     plt.suptitle(title, x=0.5, y=0.99)
     plt.tight_layout()
     filename = os.path.join(output_folder, name + ".png")
@@ -96,7 +95,7 @@ def summary_plot(args, energy_source, summary_df, output_folder, name):
     energy_components = PowerSourceMap[energy_source]
     col_num = len(energy_components)
     fig, axes = plt.subplots(col_num, 1, figsize=(plot_width, plot_height * col_num))
-    for i in range(0, col_num):
+    for i in range(col_num):
         component = energy_components[i]
         data = summary_df[(summary_df["energy_source"] == energy_source) & (summary_df["energy_component"] == component)]
         data = data.sort_values(by=["Feature Group", "MAE"])
@@ -111,7 +110,7 @@ def summary_plot(args, energy_source, summary_df, output_folder, name):
         if i < col_num - 1:
             ax.set_xlabel("")
         ax.legend(bbox_to_anchor=(1.05, 1.05))
-    plt.suptitle("{} {} error".format(energy_source, args.output_type))
+    plt.suptitle(f"{energy_source} {args.output_type} error")
     plt.tight_layout()
     filename = os.path.join(output_folder, name + ".png")
     fig.savefig(filename)
@@ -134,7 +133,7 @@ def metadata_plot(args, energy_source, metadata_df, output_folder, name):
     energy_components = PowerSourceMap[energy_source]
     col_num = len(energy_components)
     fig, axes = plt.subplots(col_num, 1, figsize=(plot_width, plot_height * col_num))
-    for i in range(0, col_num):
+    for i in range(col_num):
         component = energy_components[i]
         metadata_df = metadata_df.sort_values(by="feature_group")
         if col_num == 1:
@@ -149,7 +148,7 @@ def metadata_plot(args, energy_source, metadata_df, output_folder, name):
         if i < col_num - 1:
             ax.set_xlabel("")
     #  ax.legend(bbox_to_anchor=(1.05, 1.05))
-    plt.suptitle("Pipieline metadata of {} {}".format(energy_source.upper(), args.output_type))
+    plt.suptitle(f"Pipieline metadata of {energy_source.upper()} {args.output_type}")
     plt.tight_layout()
     plt.legend(frameon=False)
     filename = os.path.join(output_folder, name + ".png")
@@ -174,7 +173,7 @@ def power_curve_plot(args, data_path, energy_source, output_folder, name):
 
 def _get_model(model_toppath, trainer, model_node_type, output_type, name, energy_source):
     feature_group = FeatureGroup.BPFOnly
-    model_name = "{}_{}".format(trainer, model_node_type)
+    model_name = f"{trainer}_{model_node_type}"
     group_path = get_model_group_path(model_toppath, output_type, feature_group, energy_source, name)
     model_path = os.path.join(group_path, model_name)
     model = load_model(model_path)
@@ -204,11 +203,12 @@ def _load_all_models(model_toppath, output_type, name, node_types, energy_source
 
 
 def _plot_models(models, cpu_ms_max, energy_source, output_folder, name, max_plot=15, cpu_time_bin_num=10, sample_num=20):
-    from kepler_model.util.train_types import BPF_FEATURES
     import numpy as np
     import pandas as pd
     import seaborn as sns
 
+    from kepler_model.util.train_types import BPF_FEATURES
+
     sns.set_palette("Paired")
 
     import matplotlib.pyplot as plt
@@ -253,7 +253,7 @@ def _plot_models(models, cpu_ms_max, energy_source, output_folder, name, max_plo
                 ax = axes[axes_index // num_cols][axes_index % num_cols]
             node_type = data_with_prediction_index[0]
             data_with_prediction = data_with_prediction_index[1]
-            sns.lineplot(data=data_with_prediction, x=main_feature_col, y=predicted_col[energy_source], label="type={}".format(node_type), marker=markers[index], ax=ax)
+            sns.lineplot(data=data_with_prediction, x=main_feature_col, y=predicted_col[energy_source], label=f"type={node_type}", marker=markers[index], ax=ax)
             index += 1
             index = index % len(markers)
             if index % max_plot == 0:

src/kepler_model/cmd/cmd_util.py

@@ -1,25 +1,30 @@
-import os
 import datetime
-import pandas as pd
+import os
 
+import pandas as pd
 
-from kepler_model.util.prom_types import node_info_column, prom_responses_to_results, SOURCE_COL, energy_component_to_query
-from kepler_model.util.train_types import ModelOutputType, FeatureGroup, PowerSourceMap
-from kepler_model.util.loader import load_json, get_pipeline_path, default_node_type
+from kepler_model.util.loader import default_node_type, get_pipeline_path, load_json
+from kepler_model.util.prom_types import (
+    SOURCE_COL,
+    energy_component_to_query,
+    node_info_column,
+    prom_responses_to_results,
+)
 from kepler_model.util.saver import assure_path, save_csv
+from kepler_model.util.train_types import FeatureGroup, ModelOutputType, PowerSourceMap
 
 UTC_OFFSET_TIMEDELTA = datetime.datetime.utcnow() - datetime.datetime.now()
 
 
 def print_file_to_stdout(data_path, args):
     file_path = os.path.join(data_path, args.output)
     try:
-        with open(file_path, "r") as file:
+        with open(file_path) as file:
             contents = file.read()
             print(contents)
     except FileNotFoundError:
         print(f"Error: Output '{file_path}' not found.")
-    except IOError:
+    except OSError:
         print(f"Error: Unable to read output '{file_path}'.")
 
 
@@ -41,7 +46,7 @@ def extract_time(data_path, benchmark_filename):
 
 def save_query_results(data_path, output_filename, query_response):
     query_results = prom_responses_to_results(query_response)
-    save_path = os.path.join(data_path, "{}_csv".format(output_filename))
+    save_path = os.path.join(data_path, f"{output_filename}_csv")
     assure_path(save_path)
     for query, data in query_results.items():
         save_csv(save_path, query, data)
@@ -80,13 +85,13 @@ def summary_validation(validate_df):
         no_data_df = target_df[target_df["count"] == 0]
         zero_data_df = target_df[target_df[">0"] == 0]
         valid_df = target_df[target_df[">0"] > 0]
-        print("==== {} ====".format(metric))
+        print(f"==== {metric} ====")
         if len(no_data_df) > 0:
             print("{} pods: \tNo data for {}".format(len(no_data_df), pd.unique(no_data_df["scenarioID"])))
         if len(zero_data_df) > 0:
             print("{} pods: \tZero data for {}".format(len(zero_data_df), pd.unique(zero_data_df["scenarioID"])))
 
-        print("{} pods: \tValid\n".format(len(valid_df)))
+        print(f"{len(valid_df)} pods: \tValid\n")
         print("Valid data points:")
         print("Empty" if len(valid_df[">0"]) == 0 else valid_df.groupby(["scenarioID"]).sum()[[">0"]])
     for metric, query in metric_to_validate_power.items():
@@ -246,7 +251,7 @@ def check_ot_fg(args, valid_fg):
         try:
             fg = FeatureGroup[args.feature_group]
             if args.feature_group not in valid_fg_name_list:
-                print("feature group: {} is not available in your data. please choose from the following list: {}".format(args.feature_group, valid_fg_name_list))
+                print(f"feature group: {args.feature_group} is not available in your data. please choose from the following list: {valid_fg_name_list}")
                 exit()
         except KeyError:
             print("invalid feature group: {}. valid feature group are {}.".format((args.feature_group, [fg.name for fg in valid_fg])))
@@ -268,14 +273,21 @@ def assert_train(trainer, data, energy_components):
             try:
                 output = trainer.predict(node_type, component, X_values)
                 if output is not None:
-                    assert len(output) == len(X_values), "length of predicted values != features ({}!={})".format(len(output), len(X_values))
+                    assert len(output) == len(X_values), f"length of predicted values != features ({len(output)}!={len(X_values)})"
             except sklearn.exceptions.NotFittedError:
                 pass
 
 
 def get_isolator(data_path, isolator, profile, pipeline_name, target_hints, bg_hints, abs_pipeline_name, replace_node_type=default_node_type):
     pipeline_path = get_pipeline_path(data_path, pipeline_name=pipeline_name)
-    from kepler_model.train import MinIdleIsolator, NoneIsolator, DefaultProfiler, ProfileBackgroundIsolator, TrainIsolator, generate_profiles
+    from kepler_model.train import (
+        DefaultProfiler,
+        MinIdleIsolator,
+        NoneIsolator,
+        ProfileBackgroundIsolator,
+        TrainIsolator,
+        generate_profiles,
+    )
 
     supported_isolator = {
         MinIdleIsolator().get_name(): MinIdleIsolator(),
@@ -306,13 +318,12 @@ def get_isolator(data_path, isolator, profile, pipeline_name, target_hints, bg_h
         if abs_pipeline_name != "":
             trainer_isolator = TrainIsolator(idle_data=idle_data, profiler=DefaultProfiler, target_hints=target_hints, bg_hints=bg_hints, abs_pipeline_name=abs_pipeline_name)
             supported_isolator[trainer_isolator.get_name()] = trainer_isolator
-    else:
-        if abs_pipeline_name != "":
-            trainer_isolator = TrainIsolator(target_hints=target_hints, bg_hints=bg_hints, abs_pipeline_name=abs_pipeline_name)
-            supported_isolator[trainer_isolator.get_name()] = trainer_isolator
+    elif abs_pipeline_name != "":
+        trainer_isolator = TrainIsolator(target_hints=target_hints, bg_hints=bg_hints, abs_pipeline_name=abs_pipeline_name)
+        supported_isolator[trainer_isolator.get_name()] = trainer_isolator
 
     if isolator not in supported_isolator:
-        print("isolator {} is not supported. supported isolator: {}".format(isolator, supported_isolator.keys()))
+        print(f"isolator {isolator} is not supported. supported isolator: {supported_isolator.keys()}")
         return None
     return supported_isolator[isolator]
 
@@ -322,7 +333,7 @@ def get_extractor(extractor):
 
     supported_extractor = {DefaultExtractor().get_name(): DefaultExtractor(), SmoothExtractor().get_name(): SmoothExtractor()}
     if extractor not in supported_extractor:
-        print("extractor {} is not supported. supported extractor: {}".format(extractor, supported_extractor.keys()))
+        print(f"extractor {extractor} is not supported. supported extractor: {supported_extractor.keys()}")
         return None
     return supported_extractor[extractor]