Merge branch 'master' of https://github.com/jatinpapreja/practical-nlp

Author: kartikay-bagla

Ch2/03_Extracting_text_from_images_tesseract.ipynb

@@ -31,7 +31,10 @@
    },
    "outputs": [],
    "source": [
-    "!sudo apt install tesseract-ocr\n",
+    "import os\n",
+    "if (os.name) != \"nt\":\n",
+    "    print(\"Not using Windows\")\n",
+    "    !sudo apt install tesseract-ocr\n",
     "!pip install pytesseract"
    ]
   },
@@ -50,18 +53,6 @@
     "4. Set the tesseract path in the script before calling image_to_string."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# ONLY FOR WINDOWS USERS\n",
-    "# Setting the tesseract path in the script before calling image_to_string.\n",
-    "import pytesseract\n",
-    "pytesseract.pytesseract.tesseract_cmd = r'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'  "
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -82,7 +73,12 @@
     "#making the necessary imports\n",
     "import pytesseract\n",
     "from pytesseract import image_to_string\n",
-    "from PIL import Image"
+    "from PIL import Image\n",
+    "\n",
+    "# ONLY FOR WINDOWS USERS\n",
+    "# Setting the tesseract path in the script before calling image_to_string.\n",
+    "if (os.name) == \"nt\":\n",
+    "    pytesseract.pytesseract.tesseract_cmd = r'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'"
    ]
   },
   {
@@ -120,9 +116,12 @@
    },
    "outputs": [],
    "source": [
-    "#uploading an image into colab\n",
-    "# from google.colab import files\n",
-    "# uploaded = files.upload()"
+    "# uploading an image into colab\n",
+    "try:\n",
+    "    from google.colab import files\n",
+    "    uploaded = files.upload()\n",
+    "except ModuleNotFoundError:\n",
+    "    print(\"Not using colab\")"
    ]
   },
   {
@@ -216,7 +215,36 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.4"
+   "version": "3.6.8"
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
   }
  },
  "nbformat": 4,

Ch3/09_Visualizing_Embeddings_Using_TSNE.ipynb

@@ -41,11 +41,13 @@
    },
    "outputs": [],
    "source": [
-    "#upload the \"word2vec.bin\" file in form the repository which can be found in the same folder as this notebook.\n",
-    "\n",
     "# FOR GOOGLE COLAB USERS\n",
-    "# from google.colab import files\n",
-    "# uploaded = files.upload()"
+    "# upload the \"word2vec.bin\" file in form the repository which can be found in the same folder as this notebook.\n",
+    "try:\n",
+    "    from google.colab import files\n",
+    "    uploaded = files.upload()\n",
+    "except ModuleNotFoundError:\n",
+    "    print(\"Not using colab\")"
    ]
   },
   {
@@ -393,7 +395,36 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.0"
+   "version": "3.6.8"
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
   }
  },
  "nbformat": 4,