[FEAT] Add colab badges to docs (#165)

Nixtla · Nov 9, 2023 · e0dcc35 · e0dcc35
2 parents bb46813 + 7e1cd4f
commit e0dcc35
Show file tree

Hide file tree

Showing 18 changed files with 563 additions and 45 deletions.
diff --git a/.fernignore b/.fernignore
@@ -16,6 +16,7 @@ settings.ini
 setup.py
 pyproject.toml
 nixtlats/timegpt.py
+nixtlats/utils.py
 nixtlats/_modidx.py
 nixtlats/__init__.py
 nixtlats/distributed/

diff --git a/action_files/create_sdk_reference.py b/action_files/create_sdk_reference.py
@@ -8,12 +8,12 @@
 
 
 def create_sdk_reference(
-        save_dir,
-        slug_number,
-        host_url=os.environ['README_HOST_URL'], 
-        category=os.environ['README_CATEGORY'],
-    ):
-    file_path = f'{save_dir}/{slug_number}_sdk_reference.md'
+    save_dir,
+    slug_number,
+    host_url=os.environ["README_HOST_URL"],
+    category=os.environ["README_CATEGORY"],
+):
+    file_path = f"{save_dir}/{slug_number}_sdk_reference.md"
     header = f"""---
 title: "SDK Reference"
 slug: "sdk_reference"
@@ -25,10 +25,10 @@ def create_sdk_reference(
 ---
 
     """
-    
-    with open(file_path, 'w', encoding='utf-8') as file:
+
+    with open(file_path, "w", encoding="utf-8") as file:
         file.write(header)
 
-if __name__=="__main__":
-    fire.Fire(create_sdk_reference)
 
+if __name__ == "__main__":
+    fire.Fire(create_sdk_reference)
diff --git a/action_files/modify_markdown.py b/action_files/modify_markdown.py
@@ -9,26 +9,28 @@
 
 def to_snake_case(s):
     s = s.lower()
-    s = re.sub(r'(?<!^)(?=[A-Z])', '_', s).lower()
-    s = re.sub(r'\W', '_', s)
-    s = re.sub(r'_+', '_', s)
+    s = re.sub(r"(?<!^)(?=[A-Z])", "_", s).lower()
+    s = re.sub(r"\W", "_", s)
+    s = re.sub(r"_+", "_", s)
     return s
 
+
 def merge_lines(md_text):
-    code_block_pattern = re.compile(r'``` python([\s\S]*?)```', re.MULTILINE)
+    code_block_pattern = re.compile(r"``` python([\s\S]*?)```", re.MULTILINE)
     code_blocks = code_block_pattern.findall(md_text)
-    md_text_no_code = code_block_pattern.sub('CODEBLOCK', md_text)
-    lines = md_text_no_code.split('\n')
+    md_text_no_code = code_block_pattern.sub("CODEBLOCK", md_text)
+    lines = md_text_no_code.split("\n")
     merged_lines = []
     buffer_line = ""
     in_div_block = False
     for line in lines:
-        if line.strip().lower().startswith('<div>'):
+        if line.strip().lower().startswith("<div>"):
             in_div_block = True
-        elif line.strip().lower().endswith('</div>'):
+        elif line.strip().lower().endswith("</div>"):
             in_div_block = False
-        if (in_div_block or 
-            line.startswith(('    ', '> ', '#', '-', '*', '1.', '2.', '3.', 'CODEBLOCK', '!', '['))):
+        if in_div_block or line.startswith(
+            ("    ", "> ", "#", "-", "*", "1.", "2.", "3.", "CODEBLOCK", "!", "[")
+        ):
             if buffer_line:
                 merged_lines.append(buffer_line.strip())
                 buffer_line = ""
@@ -37,34 +39,37 @@ def merge_lines(md_text):
             buffer_line += line.strip() + " "
     if buffer_line:
         merged_lines.append(buffer_line.strip())
-    md_text_merged = '\n'.join(merged_lines)
+    md_text_merged = "\n".join(merged_lines)
     for code_block in code_blocks:
-        md_text_merged = md_text_merged.replace('CODEBLOCK', f'\n``` python\n{code_block}\n```\n', 1)
+        md_text_merged = md_text_merged.replace(
+            "CODEBLOCK", f"\n``` python\n{code_block}\n```\n", 1
+        )
     return md_text_merged
 
+
 def modify_markdown(
-        file_path, 
-        slug_number=0,
-        host_url=os.environ['README_HOST_URL'], 
-        category=os.environ['README_CATEGORY'],
-    ):
-    with open(file_path, 'r', encoding='utf-8') as file:
+    file_path,
+    slug_number=0,
+    host_url=os.environ["README_HOST_URL"],
+    category=os.environ["README_CATEGORY"],
+):
+    with open(file_path, "r", encoding="utf-8") as file:
         content = file.read()
     dir_path = os.path.dirname(file_path)
     if not dir_path.endswith("/"):
         dir_path += "/"
-    
+
     # Extract and remove the first markdown header
-    pattern_header = re.compile(r'^#\s+(.*)\n+', re.MULTILINE)
+    pattern_header = re.compile(r"^#\s+(.*)\n+", re.MULTILINE)
     match = pattern_header.search(content)
-    
+
     if match:
         title = match.group(1)
-        content = pattern_header.sub('', content, count=1) # remove the first match
+        content = pattern_header.sub("", content, count=1)  # remove the first match
     else:
-        title = 'Something Amazing'
+        title = "Something Amazing"
     slug = to_snake_case(title)
-    
+
     # Prepare the new header
     header = f"""---
 title: "{title}"
@@ -76,22 +81,24 @@ def modify_markdown(
 ---
 
     """
-    
+
     # Remove parts delimited by ::: :::
-    pattern_delimited = re.compile(r':::.*?:::', re.DOTALL)  
-    content = pattern_delimited.sub('', content)
+    pattern_delimited = re.compile(r":::.*?:::", re.DOTALL)
+    content = pattern_delimited.sub("", content)
 
     # Modify image paths
-    pattern_image = re.compile(r'!\[\]\((.*?)\)')
-    content = content.replace('![figure](../../', f'![figure]({host_url}/nbs/')
-    modified_content = pattern_image.sub(r'![](' + host_url + dir_path + r'\1)', content)
+    content = content.replace("![figure](../../", f"![figure]({host_url}/nbs/")
+    pattern_image = re.compile(r"!\[\]\(((?!\.svg)*?)\)")
+    modified_content = pattern_image.sub(
+        r"![](" + host_url + dir_path + r"\1)", content
+    )
 
     # Concatenate new header and modified content
     final_content = header + merge_lines(modified_content)
-    
-    with open(file_path, 'w', encoding='utf-8') as file:
+
+    with open(file_path, "w", encoding="utf-8") as file:
         file.write(final_content)
 
-if __name__=="__main__":
-    fire.Fire(modify_markdown)
 
+if __name__ == "__main__":
+    fire.Fire(modify_markdown)
diff --git a/nbs/docs/getting-started/1_getting_started_short.ipynb b/nbs/docs/getting-started/1_getting_started_short.ipynb
@@ -10,6 +10,41 @@
     "> Unlock the power of accurate predictions and confidently navigate uncertainty. Reduce uncertainty and resource limitations. With TimeGPT, you can effortlessly access state-of-the-art models to make data-driven decisions. Whether you're a bank forecasting market trends or a startup predicting product demand, TimeGPT democratizes access to cutting-edge predictive insights."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fb455c30-d11d-49a1-8825-c908328bc63a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "from nixtlats.utils import colab_badge"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f2820d3a-47dd-4827-925f-63f454701c79",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/getting-started/1_getting_started_short.ipynb)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#| echo: false\n",
+    "colab_badge('docs/getting-started/1_getting_started_short')"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "568b7aba-5990-477b-a012-9bd30815cfe3",

diff --git a/nbs/docs/how-to-guides/0_distributed_fcst_spark.ipynb b/nbs/docs/how-to-guides/0_distributed_fcst_spark.ipynb
@@ -11,6 +11,41 @@
     "`TimeGPT` works on top of Spark, Dask, and Ray through Fugue. `TimeGPT` will read the input DataFrame and use the corresponding engine. For example, if the input is a Spark DataFrame, StatsForecast will use the existing Spark session to run the forecast.\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a3119cd0-9b9d-4df9-9779-005847c46048",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "from nixtlats.utils import colab_badge"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dbd11fae-3219-4ffc-b2de-a96542362d58",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/how-to-guides/0_distributed_fcst_spark.ipynb)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#| echo: false\n",
+    "colab_badge('docs/how-to-guides/0_distributed_fcst_spark')"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "361d702c-361f-4321-85d3-2b76fb7b4937",

diff --git a/nbs/docs/how-to-guides/1_distributed_cv_spark.ipynb b/nbs/docs/how-to-guides/1_distributed_cv_spark.ipynb
@@ -11,6 +11,41 @@
     "`TimeGPT` works on top of Spark, Dask, and Ray through Fugue. `TimeGPT` will read the input DataFrame and use the corresponding engine. For example, if the input is a Spark DataFrame, StatsForecast will use the existing Spark session to run the forecast.\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5051a20b-716a-4e83-ab9a-6472c7e4a4fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "from nixtlats.utils import colab_badge"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9ec6d4ad-7514-4ee9-8ca5-2ef027c45e6a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/how-to-guides/1_distributed_cv_spark.ipynb)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#| echo: false\n",
+    "colab_badge('docs/how-to-guides/1_distributed_cv_spark')"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "361d702c-361f-4321-85d3-2b76fb7b4937",

diff --git a/nbs/docs/tutorials/0_anomaly_detection.ipynb b/nbs/docs/tutorials/0_anomaly_detection.ipynb
@@ -16,6 +16,41 @@
     "Anomaly detection in time series data plays a pivotal role in numerous sectors including finance, healthcare, security, and infrastructure. In essence, time series data represents a sequence of data points indexed (or listed or graphed) in time order, often with equal intervals. As systems and processes become increasingly digitized and interconnected, the need to monitor and ensure their normal behavior grows proportionally. Detecting anomalies can indicate potential problems, malfunctions, or even malicious activities. By promptly identifying these deviations from the expected pattern, organizations can take preemptive measures, optimize processes, or protect resources. `TimeGPT` includes the `detect_anomalies` method to detect anomalies automatically."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "db88512e-9e9e-4f01-83a6-bec1ccdbff8e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "from nixtlats.utils import colab_badge"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7528cf16-4e82-4ea0-bfe0-4d55fa71db0c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/tutorials/0_anomaly_detection.ipynb)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#| echo: false\n",
+    "colab_badge('docs/tutorials/0_anomaly_detection')"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

diff --git a/nbs/docs/tutorials/1_exogenous_variables.ipynb b/nbs/docs/tutorials/1_exogenous_variables.ipynb
@@ -20,6 +20,41 @@
     "To incorporate exogenous variables in TimeGPT, you'll need to pair each point in your time series data with the corresponding external data."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "44ec954b-63b3-4236-86a5-5a2cd86de934",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "from nixtlats.utils import colab_badge"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0bc1e229-6c80-463f-b721-465a48fbddf1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Nixtla/nixtla/blob/main/nbs/docs/tutorials/1_exogenous_variables.ipynb)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#| echo: false\n",
+    "colab_badge('docs/tutorials/1_exogenous_variables')"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,