datfid 0.1.12__py3-none-any.whl → 0.1.13__py3-none-any.whl

datfid-0.1.13.dist-info/METADATA

@@ -0,0 +1,155 @@
+Metadata-Version: 2.4
+Name: datfid
+Version: 0.1.13
+Summary: SDK to access the DATFID API hosted on Hugging Face Spaces
+Author: DATFID
+Author-email: igor.schapiro@datfid.com
+License: MIT
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.31.0
+Requires-Dist: pandas>=1.0.1
+Requires-Dist: numpy<2.1,>=1.22
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# DATFID SDK
+
+A Python SDK to access the DATFID API to forecast your data.
+
+## Features
+
+- **Easy model fitting**: Build panel data models with time-dependent and static features.
+- **Flexible lag handling**: Specify lags for the dependent variable and selected features.
+- **Forecasting**: Generate future predictions with aligned timestamps and IDs.
+- **Statistical options**: Filter features by significance and apply mean-variance tests.
+- **White box full interpretability**: Get fully interpretable model with equation, estimated parameters, and standard errors.
+
+## Installation
+
+```bash
+pip install datfid
+```
+
+## Usage
+
+Before using the SDK, please request an access token by emailing **admin@datfid.com** or by visiting our website [datfid.com](https://datfid.com).
+
+```python
+from datfid import DATFIDClient
+
+# Initialize the client with your DATFID token
+client = DATFIDClient(token="your_DATFID_token")
+
+# Fit a model
+fit_result = client.fit_model(
+    df=dataframe,
+    id_col="name of id column",
+    time_col="name of time column",
+    y="name of dependent variable",
+    lag_y="starting lag : ending lag",
+    lagged_features={
+        "feature 1": "starting lag : ending lag",
+        "feature 2": "starting lag : ending lag"
+    },
+    current_features=["feature 3", "feature 4"],
+    filter_by_significance=True/False,
+    meanvar_test=True/False
+)
+
+# Generate forecasts
+forecast_df = client.forecast_model(
+    df_forecast=dataframe
+)
+
+# The forecast DataFrame contains the individual IDs and timestamps
+# from the original data plus a "forecast" column with predicted values.
+```
+
+## Example 1
+
+Sample dataset from GitHub (Food and Beverages demand forecasting):
+
+```python
+import pandas as pd
+from datfid import DATFIDClient
+
+# Initialize the client with your DATFID token
+client = DATFIDClient(token="your_DATFID_token")
+
+# Load dataset for model fitting
+url_fit = "https://raw.githubusercontent.com/datfid-valeriidashuk/sample-datasets/main/Food_Beverages.xlsx"
+df = pd.read_excel(url_fit)
+
+# Fit the model
+result = client.fit_model(df=df,
+                          id_col="Product",
+                          time_col="Time",
+                          y="Revenue",
+                          current_features='all',
+                          filter_by_significance=True
+                          )
+
+# Load dataset for forecasting
+url_forecast = "https://raw.githubusercontent.com/datfid-valeriidashuk/sample-datasets/main/Food_Beverages_forecast.xlsx"
+df_forecast = pd.read_excel(url_forecast)
+
+# Forecast revenue using the fitted model
+forecast = client.forecast_model(df_forecast=df_forecast)
+```
+
+## Example 2
+
+Slightly larger sample dataset from GitHub (Banking sector, forecasting loan probability):
+
+```python
+import pandas as pd
+from datfid import DATFIDClient
+
+# Initialize the client with your DATFID token
+client = DATFIDClient(token="your_DATFID_token")
+
+# Load dataset for model fitting
+url_fit = "https://raw.githubusercontent.com/datfid-valeriidashuk/sample-datasets/main/Banking_extended.xlsx"
+df = pd.read_excel(url_fit)
+
+# Fit the model
+result = client.fit_model(df=df,
+                          id_col="Individual",
+                          time_col="Time",
+                          y="Loan Probability",
+                          lag_y="1:3",
+                          lagged_features={"Income Level": "1:3"},
+                          filter_by_significance=True)
+
+# Load dataset for forecasting
+url_forecast = "https://raw.githubusercontent.com/datfid-valeriidashuk/sample-datasets/main/Banking_extended_forecast.xlsx"
+df_forecast = pd.read_excel(url_forecast)
+
+# Forecast loan probability using the fitted model
+forecast = client.forecast_model(df_forecast=df_forecast)
+```
+
+## API Reference
+
+### DATFIDClient
+
+#### `client = DATFIDClient(token: str)`
+Initialize the client with your DATFID token.
+
+#### `client.fit_model(df: pd.DataFrame, id_col: str, time_col: str, y: str, lag_y: Optional[Union[int, str, list[int]]] = None, lagged_features: Optional[Dict[str, int]] = None, current_features: Optional[list] = None, filter_by_significance: bool = False, meanvar_test: bool = False) -> SimpleNamespace`
+Fit a model using the provided dataset.
+
+#### `client.forecast_model(df_forecast: pd.DataFrame) -> pd.DataFrame`
+Generate forecasts using the fitted model.

datfid-0.1.13.dist-info/RECORD

@@ -0,0 +1,7 @@
+datfid/__init__.py,sha256=PojdUQsimZvawR8lgqVpzs3EkRtkA7iwuDk7fovJF54,34
+datfid/client.py,sha256=XH8wTBsHOHT3Fl1DzDWP9PfIUxJGg24eLH7_cWuymic,4656
+datfid-0.1.13.dist-info/licenses/LICENSE,sha256=5b2JLb1-P8Nt919phjUmP0umS82SxGMlIF2QFn9ILgM,1084
+datfid-0.1.13.dist-info/METADATA,sha256=fleRinV54vP271uLNgLk5sTyQDy4zxw-edkcF3dSIjE,5146
+datfid-0.1.13.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datfid-0.1.13.dist-info/top_level.txt,sha256=VFG23u9NMNQJ8S_IFfW-S5d8oSUd71SFA346ovh_uxA,7
+datfid-0.1.13.dist-info/RECORD,,

datfid-0.1.12.dist-info/METADATA

@@ -1,87 +0,0 @@
-Metadata-Version: 2.4
-Name: datfid
-Version: 0.1.12
-Summary: SDK to access the DATFID API hosted on Hugging Face Spaces
-Author: DATFID
-Author-email: igor.schapiro@datfid.com
-License: MIT
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Requires-Python: >=3.7
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: requests>=2.31.0
-Requires-Dist: pandas>=1.0.1
-Requires-Dist: numpy<2.1,>=1.22
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: license
-Dynamic: license-file
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
-# DATFID SDK
-
-A Python SDK to access the DATFID API running on Hugging Face Spaces.
-
-## Installation
-
-```bash
-pip install datfid
-```
-
-## Usage
-
-```python
-from datfid import DATFIDClient
-
-# Initialize the client with your Hugging Face token
-client = DATFIDClient(token="your_huggingface_token")
-
-# Fit a model
-fit_result = client.fit_model(
-    file_path="path/to/your/data.xlsx",
-    id_col="Individual",
-    time_col="Time",
-    y="Loan Probability",
-    lagged_features={"Repayment Amount": 1, "Missed Payments": 2},
-    current_features=["Credit Score", "Unemployment Rate"],
-    filter_by_significance=True,
-    meanvar_test=False
-)
-
-# Generate forecasts
-forecast_df = client.generate_forecast(
-    file_path="path/to/your/forecast_data.xlsx",
-    id_col="Individual",
-    time_col="Time",
-    y="Loan Probability",
-    lagged_features={"Repayment Amount": 1, "Missed Payments": 2},
-    current_features=["Credit Score", "Unemployment Rate"],
-    filter_by_significance=True,
-    meanvar_test=False
-)
-
-# The forecast DataFrame includes the original data plus forecast columns:
-# - forecast: The predicted values
-# - forecast_lower: Lower bound of the prediction interval
-# - forecast_upper: Upper bound of the prediction interval
-# - forecast_error: Standard error of the forecast
-```
-
-## API Reference
-
-### DATFIDClient
-
-#### `__init__(token: str)`
-Initialize the client with your Hugging Face token.
-
-#### `fit_model(file_path: str, id_col: str, time_col: str, y: str, lagged_features: Optional[Dict[str, int]] = None, current_features: Optional[list] = None, filter_by_significance: bool = False, meanvar_test: bool = False) -> Dict[str, Any]`
-Fit a model using the provided data.
-
-#### `generate_forecast(file_path: str, id_col: str, time_col: str, y: str, lagged_features: Optional[Dict[str, int]] = None, current_features: Optional[list] = None, filter_by_significance: bool = False, meanvar_test: bool = False) -> pd.DataFrame`
-Generate forecasts using the fitted model.

datfid-0.1.12.dist-info/RECORD

@@ -1,7 +0,0 @@
-datfid/__init__.py,sha256=PojdUQsimZvawR8lgqVpzs3EkRtkA7iwuDk7fovJF54,34
-datfid/client.py,sha256=XH8wTBsHOHT3Fl1DzDWP9PfIUxJGg24eLH7_cWuymic,4656
-datfid-0.1.12.dist-info/licenses/LICENSE,sha256=5b2JLb1-P8Nt919phjUmP0umS82SxGMlIF2QFn9ILgM,1084
-datfid-0.1.12.dist-info/METADATA,sha256=cTQxUumLGxbsYwS09JxmJJrOIcit1ZCgeKE-nenwd-I,2750
-datfid-0.1.12.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datfid-0.1.12.dist-info/top_level.txt,sha256=VFG23u9NMNQJ8S_IFfW-S5d8oSUd71SFA346ovh_uxA,7
-datfid-0.1.12.dist-info/RECORD,,