{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\n#for dirname, _, filenames in os.walk('/kaggle/input'):\n #   for filename in filenames:\n  #      print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#lulin es mala\n\n#IMPORT \n\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\nfrom matplotlib.offsetbox import AnnotationBbox, OffsetImage\n\nimport seaborn as sns\n\nimport plotly.express as px\n\nimport descartes\nimport geopandas as gpd\nfrom shapely.geometry import Point, Polygon\n\n\nimport cv2\nfrom wordcloud import WordCloud, STOPWORDS\n\n#Text Color\nfrom termcolor import colored\n\n# Librosa Libraries\nimport librosa\nimport librosa.display\nimport IPython.display as ipd\n\n#Data Preprocessing\nimport sklearn\n\nfrom sklearn.preprocessing import StandardScaler, LabelEncoder\nfrom sklearn.model_selection import train_test_split, GridSearchCV, RandomizedSearchCV\n\n#NLP\nfrom sklearn.feature_extraction.text import CountVectorizer\n\n#WordCloud\nfrom wordcloud import WordCloud, STOPWORDS\n\n#Text Processing\nimport re\nimport nltk\nnltk.download('popular')\n\n#Language Detection\n!pip install langdetect\nimport langdetect\n\n#Sentiment\nfrom textblob import TextBlob\n\n#ner\nimport spacy\n\n#Vectorizer\nfrom sklearn import feature_extraction, manifold\n\n#Word Embedding\nimport gensim.downloader as gensim_api\n\n#Topic Modeling\nimport gensim\n\n# HTML\nfrom IPython.core.display import HTML\n\nimport warnings\nwarnings.filterwarnings('ignore')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.image as mpimg\nfrom matplotlib.offsetbox import AnnotationBbox, OffsetImage\n\nimport plotly.graph_objects as go\nimport plotly.express as px\nimport descartes\nimport geopandas as gpd\nfrom shapely.geometry import Point, Polygon\nimport librosa\nimport librosa.display\nimport IPython.display as ipd\nfrom sklearn.model_selection import train_test_split\n\nfrom keras.utils import Sequence\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten, Conv1D, MaxPool1D, BatchNormalization\nfrom keras.optimizers import RMSprop,Adam\nfrom keras.applications import VGG19, VGG16, ResNet50\n\nimport sklearn\nimport warnings\nwarnings.filterwarnings('ignore')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv(\"../input/birdclef-2021/train_metadata.csv\")\ntrain_labels = pd.read_csv(\"../input/birdclef-2021/train_soundscape_labels.csv\")\n\ntest = pd.read_csv('../input/birdclef-2021/test.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_labels.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.info()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_labels.info()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test.head()\ntest.info()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train['year'] = train['date'].apply(lambda x: x.split('-')[0])\ntrain['month'] = train['date'].apply(lambda x: x.split('-')[1])\ntrain['day_of_month'] = train['date'].apply(lambda x: x.split('-')[2])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}