Skip to content

Commit

Permalink
Add files via upload
Browse files Browse the repository at this point in the history
  • Loading branch information
Abhinavkmr authored Oct 10, 2021
1 parent 90123a7 commit a313367
Show file tree
Hide file tree
Showing 6 changed files with 6 additions and 0 deletions.
1 change: 1 addition & 0 deletions Ensemble_SVM_LR_Malayalam.ipynb
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Ensemble_SVM_LR_Malayalam.ipynb","provenance":[],"collapsed_sections":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"NmxNxMi5TECW","executionInfo":{"status":"ok","timestamp":1624685064818,"user_tz":-330,"elapsed":20322,"user":{"displayName":"Abhinav Kumar","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GhN6WFfi4jSsnU9CzZnfDwqVV_KtgtD8yEnF1qt=s64","userId":"09645300777368779770"}},"outputId":"73bc084c-c68a-44c8-e1da-4730b454edbd"},"source":["from google.colab import drive\n","drive.mount('/content/drive')"],"execution_count":null,"outputs":[{"output_type":"stream","text":["Mounted at /content/drive\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"7akUl9KLBilu"},"source":["import pandas as pd\n","SVM = pd.read_csv('/content/drive/MyDrive/HASOC_2021/Sentiment_Dravidian/Malyalam/SVM_char_1-6_gram_Malayalam_74.csv')\n","LR = pd.read_csv('/content/drive/MyDrive/HASOC_2021/Sentiment_Dravidian/Malyalam/LR_char_1-6_gram_Malayalam_73.csv')"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"giZvKKReCGFd"},"source":["predictions_test_submission=(SVM+LR)/2"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":423},"id":"pwxeTE5ZC6y3","executionInfo":{"status":"ok","timestamp":1624685124940,"user_tz":-330,"elapsed":9,"user":{"displayName":"Abhinav Kumar","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GhN6WFfi4jSsnU9CzZnfDwqVV_KtgtD8yEnF1qt=s64","userId":"09645300777368779770"}},"outputId":"c606c89a-6a0f-47dc-bb4c-2f2f6127e003"},"source":["predictions_test_submission"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/html":["<div>\n","<style scoped>\n"," .dataframe tbody tr th:only-of-type {\n"," vertical-align: middle;\n"," }\n","\n"," .dataframe tbody tr th {\n"," vertical-align: top;\n"," }\n","\n"," .dataframe thead th {\n"," text-align: right;\n"," }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n"," <thead>\n"," <tr style=\"text-align: right;\">\n"," <th></th>\n"," <th>Mixed_feelings</th>\n"," <th>Negative</th>\n"," <th>Positive</th>\n"," <th>not-malayalam</th>\n"," <th>unknown_state</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <th>0</th>\n"," <td>0.382389</td>\n"," <td>0.103209</td>\n"," <td>0.186992</td>\n"," <td>0.080896</td>\n"," <td>0.246514</td>\n"," </tr>\n"," <tr>\n"," <th>1</th>\n"," <td>0.063125</td>\n"," <td>0.149519</td>\n"," <td>0.307331</td>\n"," <td>0.008070</td>\n"," <td>0.471956</td>\n"," </tr>\n"," <tr>\n"," <th>2</th>\n"," <td>0.062019</td>\n"," <td>0.145768</td>\n"," <td>0.394981</td>\n"," <td>0.036823</td>\n"," <td>0.360409</td>\n"," </tr>\n"," <tr>\n"," <th>3</th>\n"," <td>0.002211</td>\n"," <td>0.003588</td>\n"," <td>0.015616</td>\n"," <td>0.891508</td>\n"," <td>0.087077</td>\n"," </tr>\n"," <tr>\n"," <th>4</th>\n"," <td>0.005525</td>\n"," <td>0.006591</td>\n"," <td>0.957715</td>\n"," <td>0.006389</td>\n"," <td>0.023780</td>\n"," </tr>\n"," <tr>\n"," <th>...</th>\n"," <td>...</td>\n"," <td>...</td>\n"," <td>...</td>\n"," <td>...</td>\n"," <td>...</td>\n"," </tr>\n"," <tr>\n"," <th>1957</th>\n"," <td>0.015721</td>\n"," <td>0.281389</td>\n"," <td>0.389391</td>\n"," <td>0.000267</td>\n"," <td>0.313233</td>\n"," </tr>\n"," <tr>\n"," <th>1958</th>\n"," <td>0.008293</td>\n"," <td>0.015068</td>\n"," <td>0.034317</td>\n"," <td>0.011154</td>\n"," <td>0.931168</td>\n"," </tr>\n"," <tr>\n"," <th>1959</th>\n"," <td>0.102701</td>\n"," <td>0.167398</td>\n"," <td>0.432741</td>\n"," <td>0.003643</td>\n"," <td>0.293517</td>\n"," </tr>\n"," <tr>\n"," <th>1960</th>\n"," <td>0.101695</td>\n"," <td>0.344980</td>\n"," <td>0.318964</td>\n"," <td>0.002100</td>\n"," <td>0.232261</td>\n"," </tr>\n"," <tr>\n"," <th>1961</th>\n"," <td>0.191514</td>\n"," <td>0.262473</td>\n"," <td>0.400789</td>\n"," <td>0.003091</td>\n"," <td>0.142132</td>\n"," </tr>\n"," </tbody>\n","</table>\n","<p>1962 rows × 5 columns</p>\n","</div>"],"text/plain":[" Mixed_feelings Negative Positive not-malayalam unknown_state\n","0 0.382389 0.103209 0.186992 0.080896 0.246514\n","1 0.063125 0.149519 0.307331 0.008070 0.471956\n","2 0.062019 0.145768 0.394981 0.036823 0.360409\n","3 0.002211 0.003588 0.015616 0.891508 0.087077\n","4 0.005525 0.006591 0.957715 0.006389 0.023780\n","... ... ... ... ... ...\n","1957 0.015721 0.281389 0.389391 0.000267 0.313233\n","1958 0.008293 0.015068 0.034317 0.011154 0.931168\n","1959 0.102701 0.167398 0.432741 0.003643 0.293517\n","1960 0.101695 0.344980 0.318964 0.002100 0.232261\n","1961 0.191514 0.262473 0.400789 0.003091 0.142132\n","\n","[1962 rows x 5 columns]"]},"metadata":{"tags":[]},"execution_count":4}]},{"cell_type":"code","metadata":{"id":"yx6tspZ0CJsv"},"source":["import numpy as np\n","predictions_test_submission = np.asarray(predictions_test_submission)"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"yhvtEGcuCMKO"},"source":["import numpy as np\n","predictions_test_submission1 = np.zeros_like(predictions_test_submission)\n","predictions_test_submission1[np.arange(len(predictions_test_submission)), predictions_test_submission.argmax(1)] = 1"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"UFz5rdWVDil_","executionInfo":{"status":"ok","timestamp":1624685131170,"user_tz":-330,"elapsed":3,"user":{"displayName":"Abhinav Kumar","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GhN6WFfi4jSsnU9CzZnfDwqVV_KtgtD8yEnF1qt=s64","userId":"09645300777368779770"}},"outputId":"64d670ec-cb71-45a5-aa4b-4973f4ec7dc9"},"source":["predictions_test_submission1"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["array([[1., 0., 0., 0., 0.],\n"," [0., 0., 0., 0., 1.],\n"," [0., 0., 1., 0., 0.],\n"," ...,\n"," [0., 0., 1., 0., 0.],\n"," [0., 1., 0., 0., 0.],\n"," [0., 0., 1., 0., 0.]])"]},"metadata":{"tags":[]},"execution_count":7}]},{"cell_type":"code","metadata":{"id":"EcEP5VhyDktU"},"source":["predictions_test_submission1_final = np.argmax(predictions_test_submission1, axis=1)"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"z_-UdPnAFOfo","executionInfo":{"status":"ok","timestamp":1624685133667,"user_tz":-330,"elapsed":7,"user":{"displayName":"Abhinav Kumar","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GhN6WFfi4jSsnU9CzZnfDwqVV_KtgtD8yEnF1qt=s64","userId":"09645300777368779770"}},"outputId":"02518122-bb6f-4902-fb96-ee8a39d1f3e1"},"source":["predictions_test_submission1_final"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["array([0, 4, 2, ..., 2, 1, 2])"]},"metadata":{"tags":[]},"execution_count":9}]},{"cell_type":"code","metadata":{"id":"yj7AcwqbmTKP"},"source":["import pandas as pd \n","data_train = pd.read_csv('/content/drive/MyDrive/HASOC_2021/Sentiment_Dravidian/Malyalam/Mal_sentiment_full_train.tsv', sep = '\\t')\n","data_val = pd.read_csv('/content/drive/MyDrive/HASOC_2021/Sentiment_Dravidian/Malyalam/Mal_sentiment_full_dev.tsv', sep = '\\t')\n","data_test = pd.read_csv('/content/drive/MyDrive/HASOC_2021/Sentiment_Dravidian/Malyalam/Mal_sentiment_full_test_withoutlabels.tsv', sep = '\\t')"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"ZnuYD4aqTkWk","executionInfo":{"status":"ok","timestamp":1624685178312,"user_tz":-330,"elapsed":658,"user":{"displayName":"Abhinav Kumar","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GhN6WFfi4jSsnU9CzZnfDwqVV_KtgtD8yEnF1qt=s64","userId":"09645300777368779770"}},"outputId":"7dd716ae-503c-42c0-8096-0691658b4f7b"},"source":["from sklearn import preprocessing\n","import numpy as np\n","\n","le = preprocessing.LabelEncoder()\n","\n","le.fit(data_train['category'])\n","print(le.classes_)\n","\n","y_train_index = le.transform(data_train['category'])\n","y_val_index = le.transform(data_val['category'])"],"execution_count":null,"outputs":[{"output_type":"stream","text":["['Mixed_feelings' 'Negative' 'Positive' 'not-malayalam' 'unknown_state']\n"],"name":"stdout"}]},{"cell_type":"code","metadata":{"id":"o5T7yAcFFpfm"},"source":["predictions_test_submission1_final1 = le.inverse_transform(predictions_test_submission1_final)"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"PSSBXvkTFze-","executionInfo":{"status":"ok","timestamp":1624685181535,"user_tz":-330,"elapsed":5,"user":{"displayName":"Abhinav Kumar","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GhN6WFfi4jSsnU9CzZnfDwqVV_KtgtD8yEnF1qt=s64","userId":"09645300777368779770"}},"outputId":"58cfe4a7-98fc-453d-afe6-a23c63270ad4"},"source":["predictions_test_submission1_final1"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["array(['Mixed_feelings', 'unknown_state', 'Positive', ..., 'Positive',\n"," 'Negative', 'Positive'], dtype=object)"]},"metadata":{"tags":[]},"execution_count":13}]},{"cell_type":"code","metadata":{"id":"otag6te-F1It"},"source":["data_test['category'] = predictions_test_submission1_final1"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":423},"id":"5ozZTPDwGiSv","executionInfo":{"status":"ok","timestamp":1624685186909,"user_tz":-330,"elapsed":6,"user":{"displayName":"Abhinav Kumar","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GhN6WFfi4jSsnU9CzZnfDwqVV_KtgtD8yEnF1qt=s64","userId":"09645300777368779770"}},"outputId":"4f1f70e7-af9b-4645-9a2c-ff4336200777"},"source":["data_test"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/html":["<div>\n","<style scoped>\n"," .dataframe tbody tr th:only-of-type {\n"," vertical-align: middle;\n"," }\n","\n"," .dataframe tbody tr th {\n"," vertical-align: top;\n"," }\n","\n"," .dataframe thead th {\n"," text-align: right;\n"," }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n"," <thead>\n"," <tr style=\"text-align: right;\">\n"," <th></th>\n"," <th>id</th>\n"," <th>text</th>\n"," <th>category</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <th>0</th>\n"," <td>Mal_1</td>\n"," <td>Teaserinu kurach samayamkoodi mathram. Cant wa...</td>\n"," <td>Mixed_feelings</td>\n"," </tr>\n"," <tr>\n"," <th>1</th>\n"," <td>Mal_2</td>\n"," <td>അപ്പോൾ കഥയുടെ റൂട്ട് മാറിയല്ലോ...</td>\n"," <td>unknown_state</td>\n"," </tr>\n"," <tr>\n"," <th>2</th>\n"," <td>Mal_3</td>\n"," <td>മൂത്തോൻ ട്രൈലെർ Trending List വരാത്തത് എന്താ ?</td>\n"," <td>Positive</td>\n"," </tr>\n"," <tr>\n"," <th>3</th>\n"," <td>Mal_4</td>\n"," <td>Nowadays 944k views is considered as 1M views ...</td>\n"," <td>not-malayalam</td>\n"," </tr>\n"," <tr>\n"," <th>4</th>\n"," <td>Mal_5</td>\n"," <td>Maass.trailer ennu paranja ithaanU makkale.......</td>\n"," <td>Positive</td>\n"," </tr>\n"," <tr>\n"," <th>...</th>\n"," <td>...</td>\n"," <td>...</td>\n"," <td>...</td>\n"," </tr>\n"," <tr>\n"," <th>1957</th>\n"," <td>Mal_1958</td>\n"," <td>Expression വച്ചു നോക്കുമ്പോൾ മൂക്കുത്തി കട്ടത്...</td>\n"," <td>Positive</td>\n"," </tr>\n"," <tr>\n"," <th>1958</th>\n"," <td>Mal_1959</td>\n"," <td>എനിക്ക് ഒരു 100 like തരുമോ</td>\n"," <td>unknown_state</td>\n"," </tr>\n"," <tr>\n"," <th>1959</th>\n"," <td>Mal_1960</td>\n"," <td>Nannayi onnu poliyunna lakshnm unde...Thrill m...</td>\n"," <td>Positive</td>\n"," </tr>\n"," <tr>\n"," <th>1960</th>\n"," <td>Mal_1961</td>\n"," <td>Athikam eduthu kayatti vekkenda....direction k...</td>\n"," <td>Negative</td>\n"," </tr>\n"," <tr>\n"," <th>1961</th>\n"," <td>Mal_1962</td>\n"," <td>Ithupole mooonchiya Oru padam jeevithathil kan...</td>\n"," <td>Positive</td>\n"," </tr>\n"," </tbody>\n","</table>\n","<p>1962 rows × 3 columns</p>\n","</div>"],"text/plain":[" id ... category\n","0 Mal_1 ... Mixed_feelings\n","1 Mal_2 ... unknown_state\n","2 Mal_3 ... Positive\n","3 Mal_4 ... not-malayalam\n","4 Mal_5 ... Positive\n","... ... ... ...\n","1957 Mal_1958 ... Positive\n","1958 Mal_1959 ... unknown_state\n","1959 Mal_1960 ... Positive\n","1960 Mal_1961 ... Negative\n","1961 Mal_1962 ... Positive\n","\n","[1962 rows x 3 columns]"]},"metadata":{"tags":[]},"execution_count":15}]},{"cell_type":"code","metadata":{"id":"Jt6Z80uFGjsD"},"source":["data_test.to_csv(\"/content/drive/MyDrive/HASOC_2021/Sentiment_Dravidian/Malyalam//Ensemble_SVM_LR_Malalayam.tsv\", sep=\"\\t\", index=False)"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"11fdDMTpG8QS"},"source":["check_submission = pd.read_csv(\"/content/drive/MyDrive/HASOC_2021/Sentiment_Dravidian/Malyalam//Ensemble_SVM_LR_Malalayam.tsv\", sep=\"\\t\")"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":423},"id":"uwyh-IqGG8SG","executionInfo":{"status":"ok","timestamp":1624685262383,"user_tz":-330,"elapsed":5,"user":{"displayName":"Abhinav Kumar","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GhN6WFfi4jSsnU9CzZnfDwqVV_KtgtD8yEnF1qt=s64","userId":"09645300777368779770"}},"outputId":"867f7e4a-2308-4e01-b70c-9999e9dcd1be"},"source":["check_submission"],"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/html":["<div>\n","<style scoped>\n"," .dataframe tbody tr th:only-of-type {\n"," vertical-align: middle;\n"," }\n","\n"," .dataframe tbody tr th {\n"," vertical-align: top;\n"," }\n","\n"," .dataframe thead th {\n"," text-align: right;\n"," }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n"," <thead>\n"," <tr style=\"text-align: right;\">\n"," <th></th>\n"," <th>id</th>\n"," <th>text</th>\n"," <th>category</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <th>0</th>\n"," <td>Mal_1</td>\n"," <td>Teaserinu kurach samayamkoodi mathram. Cant wa...</td>\n"," <td>Mixed_feelings</td>\n"," </tr>\n"," <tr>\n"," <th>1</th>\n"," <td>Mal_2</td>\n"," <td>അപ്പോൾ കഥയുടെ റൂട്ട് മാറിയല്ലോ...</td>\n"," <td>unknown_state</td>\n"," </tr>\n"," <tr>\n"," <th>2</th>\n"," <td>Mal_3</td>\n"," <td>മൂത്തോൻ ട്രൈലെർ Trending List വരാത്തത് എന്താ ?</td>\n"," <td>Positive</td>\n"," </tr>\n"," <tr>\n"," <th>3</th>\n"," <td>Mal_4</td>\n"," <td>Nowadays 944k views is considered as 1M views ...</td>\n"," <td>not-malayalam</td>\n"," </tr>\n"," <tr>\n"," <th>4</th>\n"," <td>Mal_5</td>\n"," <td>Maass.trailer ennu paranja ithaanU makkale.......</td>\n"," <td>Positive</td>\n"," </tr>\n"," <tr>\n"," <th>...</th>\n"," <td>...</td>\n"," <td>...</td>\n"," <td>...</td>\n"," </tr>\n"," <tr>\n"," <th>1957</th>\n"," <td>Mal_1958</td>\n"," <td>Expression വച്ചു നോക്കുമ്പോൾ മൂക്കുത്തി കട്ടത്...</td>\n"," <td>Positive</td>\n"," </tr>\n"," <tr>\n"," <th>1958</th>\n"," <td>Mal_1959</td>\n"," <td>എനിക്ക് ഒരു 100 like തരുമോ</td>\n"," <td>unknown_state</td>\n"," </tr>\n"," <tr>\n"," <th>1959</th>\n"," <td>Mal_1960</td>\n"," <td>Nannayi onnu poliyunna lakshnm unde...Thrill m...</td>\n"," <td>Positive</td>\n"," </tr>\n"," <tr>\n"," <th>1960</th>\n"," <td>Mal_1961</td>\n"," <td>Athikam eduthu kayatti vekkenda....direction k...</td>\n"," <td>Negative</td>\n"," </tr>\n"," <tr>\n"," <th>1961</th>\n"," <td>Mal_1962</td>\n"," <td>Ithupole mooonchiya Oru padam jeevithathil kan...</td>\n"," <td>Positive</td>\n"," </tr>\n"," </tbody>\n","</table>\n","<p>1962 rows × 3 columns</p>\n","</div>"],"text/plain":[" id ... category\n","0 Mal_1 ... Mixed_feelings\n","1 Mal_2 ... unknown_state\n","2 Mal_3 ... Positive\n","3 Mal_4 ... not-malayalam\n","4 Mal_5 ... Positive\n","... ... ... ...\n","1957 Mal_1958 ... Positive\n","1958 Mal_1959 ... unknown_state\n","1959 Mal_1960 ... Positive\n","1960 Mal_1961 ... Negative\n","1961 Mal_1962 ... Positive\n","\n","[1962 rows x 3 columns]"]},"metadata":{"tags":[]},"execution_count":18}]},{"cell_type":"code","metadata":{"id":"MIEN8srCnBlP"},"source":[""],"execution_count":null,"outputs":[]}]}
1 change: 1 addition & 0 deletions Ensemble_SVM_LR_RF_Kanada.ipynb

Large diffs are not rendered by default.

1 change: 1 addition & 0 deletions Ensemble_SVM_LR_TAMIL.ipynb

Large diffs are not rendered by default.

1 change: 1 addition & 0 deletions ML_Classifier_Kannada_code_mixed.ipynb

Large diffs are not rendered by default.

1 change: 1 addition & 0 deletions ML_Classifier_Malayalam_code_mixed.ipynb

Large diffs are not rendered by default.

1 change: 1 addition & 0 deletions ML_Classifier_Tamil_Sentiment (1).ipynb

Large diffs are not rendered by default.

0 comments on commit a313367

Please sign in to comment.