{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nimport pandas as pd\nimport numpy as np\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport plotly_express as px\nimport matplotlib.image as mpimg\nfrom tabulate import tabulate\nimport missingno as msno \nfrom IPython.display import display_html\nfrom PIL import Image\nimport gc\nimport cv2\nimport plotly.graph_objects as go\nfrom plotly.subplots import make_subplots\nimport matplotlib.pyplot as plt\n\nimport plotly.graph_objs as go\n\nimport pydicom # for DICOM images\nfrom skimage.transform import resize\n\n# SKLearn\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.preprocessing import OneHotEncoder\n\nimport warnings\nwarnings.filterwarnings(\"ignore\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"list(os.listdir(\"../input/osic-pulmonary-fibrosis-progression\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_PATH = \"../input/osic-pulmonary-fibrosis-progressiont/\"\n\ntrain_data = pd.read_csv('../input/osic-pulmonary-fibrosis-progression/train.csv')\ntest_data = pd.read_csv('../input/osic-pulmonary-fibrosis-progression/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data.head(5)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data.isnull().sum().sort_values(ascending=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data.isnull().sum().sort_values(ascending=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"t_smoker = train_data['SmokingStatus'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"t_smoker","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tt_smoker = pd.DataFrame(train_data['SmokingStatus'].value_counts().reset_index().values,\n                        columns=['SmokingStatus', 't_smoker'])\n\ntt_smoker = tt_smoker.sort_values('t_smoker', ascending=False)\ngroup_by = tt_smoker.groupby('SmokingStatus')['t_smoker'].sum().reset_index()\nfig = px.bar(group_by.sort_values('SmokingStatus', ascending = False)[:20][::-1], x = 'SmokingStatus', y = 't_smoker',\n            title = 'Total value counts for smokers and non smokers', text = 't_smoker', height = 500, orientation = 'v' )\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"t_sex = train_data['Sex'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"t_sex","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tt_smoker = pd.DataFrame(train_data['Sex'].value_counts().reset_index().values,\n                        columns=['Sex', 't_sex'])\n\ntt_smoker = tt_smoker.sort_values('t_sex', ascending=False)\ngroup_by = tt_smoker.groupby('Sex')['t_sex'].sum().reset_index()\nfig = px.bar(group_by.sort_values('Sex', ascending = False)[:20][::-1], x = 'Sex', y = 't_sex',\n            title = 'Total value counts for male and female', text = 't_sex', height = 500, orientation = 'v', color_discrete_sequence=['darkred'] )\nfig.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"t_percentage = train_data['Percent'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from scipy.stats import norm","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ax = sns.distplot(train_data['Percent'],\n                  bins=100,\n                  kde=True,\n                  color='skyblue',\n                  hist_kws={\"linewidth\": 15,'alpha':1})\nax.set(xlabel='Percent', ylabel='Frequency')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"xsmoker = train_data[train_data.SmokingStatus=='Ex-smoker']\ncsmoker = train_data[train_data.SmokingStatus=='Currently smokes']\nnsmoker = train_data[train_data.SmokingStatus=='Never smoked']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from plotly.offline import init_notebook_mode,iplot","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trace1 = go.Histogram(\n    x=xsmoker.Age,\n    opacity=0.75,\n    name='Ex-Smoker')\n\ntrace2 = go.Histogram(\n    x=csmoker.Age,\n    opacity=0.75,\n    name='Currently Smokes')\n\ntrace3 = go.Histogram(\n    x=nsmoker.Age,\n    opacity=0.75,\n    name='Never Smoked')\n\ndata = [trace1, trace2,trace3]\nlayout = go.Layout(barmode='stack',\n                   title='Age count according to smoking status',\n                   xaxis=dict(title='Smoker'),\n                   yaxis=dict( title='Count'),\n                   paper_bgcolor='beige',\n                   plot_bgcolor='beige'\n)\nfig = go.Figure(data=data, layout=layout)\niplot(fig)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trace1 = go.Histogram(\n    x=xsmoker.Sex,\n    opacity=0.75,\n    name='Ex-Smoker')\n\ntrace2 = go.Histogram(\n    x=csmoker.Sex,\n    opacity=0.75,\n    name='Currently Smokes')\n\ntrace3 = go.Histogram(\n    x=nsmoker.Sex,\n    opacity=0.75,\n    name='Never Smoked')\n\ndata = [trace1, trace2, trace3]\nlayout = go.Layout(barmode='stack',\n                   title='Smokers Counts According to Sex',\n                   xaxis=dict(title='Sex'),\n                   yaxis=dict( title='Count'),\n                   paper_bgcolor='beige',\n                   plot_bgcolor='beige'\n)\nfig = go.Figure(data=data, layout=layout)\niplot(fig)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_PATH","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nimport gc\nimport cv2\n\nimport pydicom # for DICOM images\nfrom skimage.transform import resize","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filename = \"/kaggle/input/osic-pulmonary-fibrosis-progression/train/ID00123637202217151272140/137.dcm\"\ndata = pydicom.dcmread(filename)\nplt.imshow(data.pixel_array, cmap=plt.cm.bone) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.imshow(data.pixel_array) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"desired_factor = ['SmokingStatus', 'Sex', 'Age',  'Percent',  'FVC',  'Weeks']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_d = train_data[desired_factor]\ntest_d = test_data[desired_factor]\ny = train_data.FVC","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_d['Sex'] = train_d['Sex'].map({'Male':1, 'Female':0})\ntrain_d['SmokingStatus'] = train_d['SmokingStatus'].map({'Ex-smoker':0, 'Currently smokes':1, 'Never smoked':2})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_d['Sex'] = test_d['Sex'].map({'Male':1, 'Female':0})\ntest_d['SmokingStatus'] = test_d['SmokingStatus'].map({'Ex-smoker':0, 'Currently smokes':1, 'Never smoked':2})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_d","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_d.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_d.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.svm import SVR","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"regressor = SVR(kernel = 'rbf')\nregressor.fit(train_d, y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = regressor.predict(train_d)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = regressor.predict(test_d)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_d['FVC'].mean()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred.mean()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv('../input/osic-pulmonary-fibrosis-progression/sample_submission.csv')\nprint(submission.shape)\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}