{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "bbfa9fa9-7275-4a00-ad8c-a156298b18e9", "metadata": { "tags": [] }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/ec2-user/anaconda3/envs/python3/lib/python3.10/site-packages/pandas/core/computation/expressions.py:21: UserWarning: Pandas requires version '2.8.0' or newer of 'numexpr' (version '2.7.3' currently installed).\n", " from pandas.core.computation.check import NUMEXPR_INSTALLED\n" ] } ], "source": [ "import pandas as pd\n", "import boto3 \n", "from datetime import datetime, date, timedelta" ] }, { "cell_type": "code", "execution_count": 2, "id": "e53e9553-fb5e-478f-b4fb-5b9db154a703", "metadata": {}, "outputs": [], "source": [ "s3 = boto3.resource('s3')\n", "bucket_name = 'dev-cucumbers'\n", "bucket = s3.Bucket(bucket_name)" ] }, { "cell_type": "code", "execution_count": 3, "id": "79cfbf19", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "['0_1699950909254637.0_20231115-013731.csv',\n", " '0_1699951409939404.8_20231114-234630.csv',\n", " '0_1699951945653548.0_20231115-023201.csv',\n", " '0_1699952549238271.5_20231115-011730.csv',\n", " '0_1699953126859277.0_20231115-010223.csv',\n", " '1_1699950909254637.0_20231115-020749.csv',\n", " '1_1699951409939404.8_20231115-001457.csv',\n", " '1_1699951945653548.0_20231115-022322.csv',\n", " '1_1699952549238271.5_20231115-002149.csv',\n", " '1_1699953126859277.0_20231115-014013.csv',\n", " '2_1699950909254637.0_20231115-003410.csv',\n", " '2_1699951409939404.8_20231114-235756.csv',\n", " '2_1699951945653548.0_20231115-012500.csv',\n", " '2_1699952549238271.5_20231115-013542.csv',\n", " '2_1699953126859277.0_20231115-012113.csv',\n", " '3_1699950909254637.0_20231115-022310.csv',\n", " '3_1699951409939404.8_20231115-000000.csv',\n", " '3_1699951945653548.0_20231115-021032.csv',\n", " '3_1699952549238271.5_20231115-015400.csv',\n", " '3_1699953126859277.0_20231115-020156.csv',\n", " '4_1699950909254637.0_20231115-022112.csv',\n", " '4_1699951409939404.8_20231115-001028.csv',\n", " '4_1699951945653548.0_20231115-023559.csv',\n", " '4_1699952549238271.5_20231115-015458.csv',\n", " '4_1699953126859277.0_20231115-014848.csv',\n", " '5_1699950909254637.0_20231115-022119.csv',\n", " '5_1699951409939404.8_20231115-001115.csv',\n", " '5_1699951945653548.0_20231115-022856.csv',\n", " '5_1699952549238271.5_20231115-020633.csv',\n", " '5_1699953126859277.0_20231115-015538.csv',\n", " '6_1699950909254637.0_20231115-020356.csv',\n", " '6_1699951409939404.8_20231114-234401.csv',\n", " '6_1699951945653548.0_20231115-021034.csv',\n", " '6_1699952549238271.5_20231115-015149.csv',\n", " '6_1699953126859277.0_20231115-015827.csv',\n", " '7_1699950909254637.0_20231115-013828.csv',\n", " '7_1699951409939404.8_20231115-001804.csv',\n", " '7_1699951945653548.0_20231115-011502.csv',\n", " '7_1699952549238271.5_20231115-021005.csv',\n", " '7_1699953126859277.0_20231115-015357.csv',\n", " '8_1699950909254637.0_20231115-020000.csv',\n", " '8_1699951409939404.8_20231115-000607.csv',\n", " '8_1699951945653548.0_20231115-021855.csv',\n", " '8_1699952549238271.5_20231115-015255.csv',\n", " '8_1699953126859277.0_20231114-225335.csv',\n", " '9_1699950909254637.0_20231115-005916.csv',\n", " '9_1699951409939404.8_20231115-000603.csv',\n", " '9_1699951945653548.0_20231115-022320.csv',\n", " '9_1699952549238271.5_20231115-005040.csv',\n", " '9_1699953126859277.0_20231115-005134.csv']" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "path = 'eimpara/Moments_2023_batches/ARIMA_chunks/Prediction_chunks/'\n", "table_names = []\n", "\n", "table_names = [obj.key.split('/')[-1] for obj in bucket.objects.filter(Prefix=path) if '/' not in obj.key.replace(path,'')]\n", "table_names = list(filter(lambda x: len(x) > 0, table_names))\n", "table_names\n", "# for obj in bucket.objects.filter(Prefix=path):\n", "# table_name = obj.key.split('/')[-1]\n", "# print(obj.key)\n", "# if len(table_name) > 0:\n", "# table_names.append(table_name)" ] }, { "cell_type": "code", "execution_count": 4, "id": "6f889031", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "50" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(table_names)\n", "# 'Fourier_table_NEW_DATA_0_20231108-111429.csv', (1207220, 6)\n", "# 'Fourier_table_NEW_DATA_1_20231109-122151.csv', (1207220, 6)\n", "# 'Fourier_table_NEW_DATA_6_20231108-191354.csv', (1207220, 6)\n", "# 'Fourier_table_NEW_DATA_7_20231109-090411.csv', (1207220, 6)\n", "# 'Fourier_table_NEW_DATA_8_20231109-091534.csv'(1207220, 6)\n" ] }, { "cell_type": "code", "execution_count": 5, "id": "8b1d4caa", "metadata": {}, "outputs": [], "source": [ "merged_df = pd.DataFrame() \n", "\n", "for table_name in table_names:\n", " obj = bucket.Object(f'{path}{table_name}')\n", " table_data = pd.read_csv(obj.get()['Body'])\n", " merged_df = pd.concat([merged_df,table_data])" ] }, { "cell_type": "code", "execution_count": 6, "id": "34637e13", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(1137500, 5)" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "merged_df.shape" ] }, { "cell_type": "code", "execution_count": 7, "id": "0d146b13", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Index: 1137500 entries, 0 to 22119\n", "Data columns (total 5 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 ISRC 1137500 non-null object \n", " 1 ACTIVITY_DATE 1137500 non-null object \n", " 2 STREAMS 1137500 non-null int64 \n", " 3 Predicted 1129375 non-null float64\n", " 4 len_df 1137500 non-null int64 \n", "dtypes: float64(1), int64(2), object(2)\n", "memory usage: 52.1+ MB\n" ] } ], "source": [ "merged_df.info()" ] }, { "cell_type": "code", "execution_count": 8, "id": "a219581d", "metadata": {}, "outputs": [], "source": [ "def save_dataframe_s3(df):\n", " s3 = boto3.client('s3')\n", " bucket_name = 'dev-cucumbers'\n", " chunks = 'CHUNKS_0178_V2'\n", " table_name = 'PREDICTION_TABLE'\n", " today = datetime.today().strftime('%Y%m%d-%H%M%S')\n", " filepath = path + table_name + '_{}_{}.csv'.format(chunks, today)\n", " csv_buffer = df.to_csv(index=False).encode('utf-8')\n", " # Save the CSV file to S3\n", " s3.put_object(Body=csv_buffer, Bucket=bucket_name, Key=filepath)\n", " print(f\"Table saved to S3 bucket: {bucket_name}, with file name: {filepath}\")\n" ] }, { "cell_type": "code", "execution_count": 9, "id": "758c2b1d", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Table saved to S3 bucket: dev-cucumbers, with file name: eimpara/Moments_2023_batches/ARIMA_chunks/Prediction_chunks/PREDICTION_TABLE_CHUNKS_0178_V2_20231115-072405.csv\n" ] } ], "source": [ "save_dataframe_s3(merged_df)" ] }, { "cell_type": "code", "execution_count": null, "id": "c10c888d", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "conda_python3", "language": "python", "name": "conda_python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.10.13" } }, "nbformat": 4, "nbformat_minor": 5 }