Skip to content

Tokenization reduction clean #327

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
elmartinj wants to merge 8 commits into
base: main
Choose a base branch
from
Open

Tokenization reduction clean #327

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
ecb840e
A cool tutorial
elmartinj Dec 2, 2025
1ae25dc
Change merging method
elmartinj Dec 2, 2025
ee9172a
run pre-comit hooks
Dec 10, 2025
f380bcb
Changing filename to requested formats and folder. This also contains…
Dec 11, 2025
af1d305
Clearance of verbose cells
Dec 11, 2025
2c14221
Staging changes to mkdocs and the naming of the tutorial file
Dec 15, 2025
bbef342
adding changes to the agent dataframe processing in order to reduce t…
elmartinj Mar 9, 2026
856e246
Merge branch 'main' into tokenization_reduction_clean
elmartinj Mar 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
85 changes: 39 additions & 46 deletions docs/examples/cryptocurrency-quickstart.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@
"outputs": [],
"source": [
"files = os.listdir(path)\n",
"files = [path + \"/\" + x for x in files]"
"files = [path+'/'+x for x in files]"
]
},
{
Expand Down Expand Up @@ -198,18 +198,18 @@
"# Read all filez and set them up to the readable structure for timecopilot\n",
"for file in files:\n",
" temp_df = pd.read_csv(file)\n",
" temp_df = temp_df[[\"Symbol\", \"Date\", \"Close\"]]\n",
" temp_df.columns = [\"unique_id\", \"ds\", \"y\"]\n",
" big_df = pd.concat([big_df, temp_df])\n",
" temp_df = temp_df[['Symbol','Date','Close']]\n",
" temp_df.columns = ['unique_id','ds','y']\n",
" big_df = pd.concat([big_df,temp_df])\n",
"\n",
"big_df = big_df.reset_index(drop=True)\n",
"big_df[\"ds\"] = pd.to_datetime(big_df[\"ds\"], dayfirst=True, errors=\"coerce\")\n",
"\n",
"# This line will be kept for execution time sanity, feel free to remove it if you want to stress timing a little further.\n",
"# This line will be kept for execution time sanity, feel free to remove it if you want to stress timing a little further. \n",
"# big_df = big_df[big_df.ds >= \"2021-01-01\"]\n",
"cryptos = [\"MIOTA\", \"XEM\", \"ETH\", \"LTC\", \"DOGE\", \"CRO\", \"USDC\", \"ADA\"]\n",
"big_df = big_df[big_df.unique_id.isin(cryptos)]\n",
"big_df = big_df.reset_index(drop=True)\n",
"cryptos=['MIOTA','XEM','ETH','LTC','DOGE','CRO','USDC','ADA']\n",
"big_df=big_df[big_df.unique_id.isin(cryptos)]\n",
"big_df=big_df.reset_index(drop=True)\n",
"big_df"
]
},
Expand Down Expand Up @@ -341,7 +341,6 @@
" df_out.loc[idx, col] = np.nan\n",
" return df_out\n",
"\n",
"\n",
"df_missing = add_missing(big_df, col=\"y\", frac=0.03, seed=42)\n",
"df_missing = df_missing.sample(frac=1, random_state=42).reset_index(drop=True)\n",
"print(df_missing)"
Expand Down Expand Up @@ -710,14 +709,12 @@
}
],
"source": [
"anomaly_summary_xlm = anomalies_df[\n",
"anomaly_summary_xlm=anomalies_df[\n",
" # (anomalies_df.unique_id=='SOL') & \\\n",
" (\n",
" (anomalies_df[\"Chronos-anomaly\"] == True)\n",
" | (anomalies_df[\"SeasonalNaive-anomaly\"] == True)\n",
" | (anomalies_df[\"Theta-anomaly\"] == True)\n",
" )\n",
"].reset_index(drop=True)\n",
" ((anomalies_df['Chronos-anomaly']==True) | \\\n",
" (anomalies_df['SeasonalNaive-anomaly']==True) |\n",
" (anomalies_df['Theta-anomaly']==True)\n",
" )].reset_index(drop=True)\n",
"anomaly_summary_xlm"
]
},
Expand Down Expand Up @@ -957,14 +954,12 @@
}
],
"source": [
"anomaly_summary_xlm = anomalies_df[\n",
" (anomalies_df.unique_id == \"ADA\")\n",
" & (\n",
" (anomalies_df[\"Chronos-anomaly\"] == True)\n",
" | (anomalies_df[\"SeasonalNaive-anomaly\"] == True)\n",
" | (anomalies_df[\"Theta-anomaly\"] == True)\n",
" )\n",
"].reset_index(drop=True)\n",
"anomaly_summary_xlm=anomalies_df[\n",
" (anomalies_df.unique_id=='ADA') & \\\n",
" ((anomalies_df['Chronos-anomaly']==True) | \\\n",
" (anomalies_df['SeasonalNaive-anomaly']==True) |\n",
" (anomalies_df['Theta-anomaly']==True)\n",
" )].reset_index(drop=True)\n",
"anomaly_summary_xlm"
]
},
Expand Down Expand Up @@ -1204,14 +1199,12 @@
}
],
"source": [
"anomaly_summary_xlm = anomalies_df[\n",
" (anomalies_df.unique_id == \"ADA\")\n",
" & (\n",
" (anomalies_df[\"Chronos-anomaly\"] == True)\n",
" & (anomalies_df[\"SeasonalNaive-anomaly\"] == True)\n",
" # (anomalies_df['Theta-anomaly']==True)\n",
" )\n",
"].reset_index(drop=True)\n",
"anomaly_summary_xlm=anomalies_df[\n",
" (anomalies_df.unique_id=='ADA') & \\\n",
" ((anomalies_df['Chronos-anomaly']==True) & \\\n",
" (anomalies_df['SeasonalNaive-anomaly']==True) \\\n",
" # (anomalies_df['Theta-anomaly']==True)\n",
" )].reset_index(drop=True)\n",
"anomaly_summary_xlm"
]
},
Expand Down Expand Up @@ -1248,12 +1241,12 @@
"source": [
"tcf1 = TimeCopilotForecaster(\n",
" models=[\n",
" AutoARIMA(),\n",
" AutoARIMA(), \n",
" Chronos(repo_id=\"amazon/chronos-bolt-mini\"),\n",
" Theta(),\n",
" AutoETS(),\n",
" Moirai(),\n",
" Prophet(),\n",
" AutoETS(), \n",
" Moirai(), \n",
" Prophet(), \n",
" SeasonalNaive(),\n",
" ]\n",
")"
Expand All @@ -1266,7 +1259,7 @@
"metadata": {},
"outputs": [],
"source": [
"fcst_df = tcf1.forecast(df=big_df, h=30, level=[80, 90])"
"fcst_df = tcf1.forecast(df=big_df, h=30, level=[80,90])"
]
},
{
Expand Down Expand Up @@ -1310,9 +1303,9 @@
"metadata": {},
"outputs": [],
"source": [
"eth_fcst_normal = fcst_df[(fcst_df.unique_id == \"ETH\")][\n",
" [\"unique_id\", \"ds\", \"Chronos\", \"Chronos-lo-80\"]\n",
"].reset_index(drop=True)"
"eth_fcst_normal=fcst_df[(fcst_df.unique_id=='ETH')]\\\n",
" [['unique_id','ds','Chronos','Chronos-lo-80']]\\\n",
" .reset_index(drop=True)"
]
},
{
Expand Down Expand Up @@ -1352,9 +1345,9 @@
"metadata": {},
"outputs": [],
"source": [
"eth_fcst_missing = fcst_df[(fcst_df.unique_id == \"ETH\")][\n",
" [\"unique_id\", \"ds\", \"Chronos\", \"Chronos-lo-80\"]\n",
"].reset_index(drop=True)"
"eth_fcst_missing=fcst_df[(fcst_df.unique_id=='ETH')]\\\n",
" [['unique_id','ds','Chronos','Chronos-lo-80']]\\\n",
" .reset_index(drop=True)"
]
},
{
Expand Down Expand Up @@ -1522,9 +1515,9 @@
}
],
"source": [
"compare = eth_fcst_normal.merge(eth_fcst_missing, on=[\"ds\", \"unique_id\"])\n",
"compare[\"dif\"] = abs(compare[\"Chronos_x\"] - compare[\"Chronos_y\"])\n",
"print(compare[\"dif\"].sum())"
"compare=eth_fcst_normal.merge(eth_fcst_missing,on=['ds','unique_id'])\n",
"compare['dif']=abs(compare['Chronos_x']-compare['Chronos_y'])\n",
"print(compare['dif'].sum())"
]
},
{
Expand Down
4 changes: 1 addition & 3 deletions mkdocs.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,12 +22,12 @@ nav:
- examples/agent-quickstart.ipynb
- examples/llm-providers.ipynb
- examples/aws-bedrock.ipynb
- examples/google-llms.ipynb
- examples/forecaster-quickstart.ipynb
- examples/anomaly-detection-forecaster-quickstart.ipynb
- examples/ts-foundation-models-comparison-quickstart.ipynb
- examples/gift-eval.ipynb
- examples/chronos-family.ipynb
- examples/crytpocurrency-quickstart.ipynb
- examples/finetuning.ipynb
- examples/cryptocurrency-quickstart.ipynb
- examples/sktime.ipynb
Expand All @@ -47,7 +47,6 @@ nav:
- api/models/ml.md
- api/models/neural.md
- api/models/ensembles.md
- api/models/adapters/adapters.md
- api/models/utils/forecaster.md
- api/gift-eval/gift-eval.md
- Changelogs:
Expand Down Expand Up @@ -76,7 +75,6 @@ nav:

theme:
name: "material"
custom_dir: docs/overrides
logo: https://timecopilot.s3.amazonaws.com/public/logos/logo-white.svg
favicon: https://timecopilot.s3.amazonaws.com/public/logos/favicon-white.svg
palette:
Expand Down
Loading
Loading