{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":20270,"databundleVersionId":1222630,"sourceType":"competition"}],"dockerImageVersionId":30380,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport os\n\nsns.set_style('darkgrid')\nplt.style.use('seaborn-notebook')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:08.629724Z","iopub.execute_input":"2025-10-26T15:56:08.630084Z","iopub.status.idle":"2025-10-26T15:56:09.280094Z","shell.execute_reply.started":"2025-10-26T15:56:08.629991Z","shell.execute_reply":"2025-10-26T15:56:09.279077Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#read in train and test csv files to calculate descriptive stats and characteristics\n\ntrain = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')\n\ntest = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:09.282383Z","iopub.execute_input":"2025-10-26T15:56:09.282725Z","iopub.status.idle":"2025-10-26T15:56:09.426056Z","shell.execute_reply.started":"2025-10-26T15:56:09.282694Z","shell.execute_reply":"2025-10-26T15:56:09.424725Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:09.427435Z","iopub.execute_input":"2025-10-26T15:56:09.427767Z","iopub.status.idle":"2025-10-26T15:56:09.454107Z","shell.execute_reply.started":"2025-10-26T15:56:09.427736Z","shell.execute_reply":"2025-10-26T15:56:09.453027Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:09.455361Z","iopub.execute_input":"2025-10-26T15:56:09.455681Z","iopub.status.idle":"2025-10-26T15:56:09.462599Z","shell.execute_reply.started":"2025-10-26T15:56:09.455654Z","shell.execute_reply":"2025-10-26T15:56:09.461384Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.info()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:09.463951Z","iopub.execute_input":"2025-10-26T15:56:09.46432Z","iopub.status.idle":"2025-10-26T15:56:09.507074Z","shell.execute_reply.started":"2025-10-26T15:56:09.464291Z","shell.execute_reply":"2025-10-26T15:56:09.505923Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:09.508421Z","iopub.execute_input":"2025-10-26T15:56:09.508732Z","iopub.status.idle":"2025-10-26T15:56:09.536874Z","shell.execute_reply.started":"2025-10-26T15:56:09.508702Z","shell.execute_reply":"2025-10-26T15:56:09.535586Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ax1 = sns.countplot(data=train, x='anatom_site_general_challenge')\nax1.set_title('Distribution of Anatomical Sites Training Set')\nax1.tick_params(axis='x', labelrotation = 45, labelsize = 12)\n\n#note: largest category by far is the torso, oral/genital is the least common category","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:09.540481Z","iopub.execute_input":"2025-10-26T15:56:09.540835Z","iopub.status.idle":"2025-10-26T15:56:09.83134Z","shell.execute_reply.started":"2025-10-26T15:56:09.540796Z","shell.execute_reply":"2025-10-26T15:56:09.830023Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ax2 = sns.countplot(data=train, x='sex')\nax2.set_title('Distribution of Gender')\n\n#note: gender is pretty evenly distributed amongst the image dataset","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:09.832861Z","iopub.execute_input":"2025-10-26T15:56:09.833321Z","iopub.status.idle":"2025-10-26T15:56:10.040973Z","shell.execute_reply.started":"2025-10-26T15:56:09.83328Z","shell.execute_reply":"2025-10-26T15:56:10.039649Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ax3 = sns.countplot(data=train, x='diagnosis')\nax3.tick_params(axis='x', labelrotation = 45, labelsize = 12)\nax3.set_title('Distribution of Diagnosis')\n\n#note: the vast majority of the images have no associated diagnosis, some have the nevus diagnosis, and very few have the melanoma diagnosis. \n#Melanoma is the target we're actually looking for.","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:10.042333Z","iopub.execute_input":"2025-10-26T15:56:10.042663Z","iopub.status.idle":"2025-10-26T15:56:10.308599Z","shell.execute_reply.started":"2025-10-26T15:56:10.042633Z","shell.execute_reply":"2025-10-26T15:56:10.307514Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ax4 = sns.countplot(data=train, x='benign_malignant')\nax4.tick_params(axis='x', labelrotation = 45, labelsize = 12)\nax4.set_title('Distribution of Diagnosis')\n\n#note: malignant here is defined as a have a \"melanoma\" disease label","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:10.310097Z","iopub.execute_input":"2025-10-26T15:56:10.310502Z","iopub.status.idle":"2025-10-26T15:56:10.521483Z","shell.execute_reply.started":"2025-10-26T15:56:10.310461Z","shell.execute_reply":"2025-10-26T15:56:10.520378Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ax5 = sns.histplot(data=train, x='age_approx', bins=18)\nax5.tick_params(axis='x', labelrotation = 45, labelsize = 12)\nax5.set_title('Distribution of Age')\n\n#age follows a normal distribution","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:10.522704Z","iopub.execute_input":"2025-10-26T15:56:10.523032Z","iopub.status.idle":"2025-10-26T15:56:10.737532Z","shell.execute_reply.started":"2025-10-26T15:56:10.522999Z","shell.execute_reply":"2025-10-26T15:56:10.736357Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print('n rows where target != benign_malignant: {}'.format(len(train.loc[(train['target'] == 1) & (train['benign_malignant'] != 'malignant')])))\nprint('n rows where benign_malignant != melanoma diagnosis: {}'.format(len(train.loc[(train['diagnosis'] != 'melanoma') & (train['benign_malignant'] == 'malignant')])))\nprint('n rows where target != benign_malignant: {}'.format(len(train.loc[(train['target'] == 1) & (train['benign_malignant'] != 'malignant')])))\n\n#my assumptions hold--this dataset is labeled based off of the 'melanoma' diagnosis, \n#and a positive value in the target column indicates a malignant melanoma tumor","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:10.738829Z","iopub.execute_input":"2025-10-26T15:56:10.739155Z","iopub.status.idle":"2025-10-26T15:56:10.760374Z","shell.execute_reply.started":"2025-10-26T15:56:10.739126Z","shell.execute_reply":"2025-10-26T15:56:10.758871Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#print the number of missing values from each col in train\nfor col in train.columns:\n    print(col + ' missing values: ' + str(train[col].isna().sum()))\n    ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:10.761578Z","iopub.execute_input":"2025-10-26T15:56:10.761926Z","iopub.status.idle":"2025-10-26T15:56:10.792529Z","shell.execute_reply.started":"2025-10-26T15:56:10.761896Z","shell.execute_reply":"2025-10-26T15:56:10.791171Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#Pull out just the observations that are positive for the target condition\nmalignant = train[train['target'] == 1]\nprint(malignant.head())\nprint(malignant.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:10.794193Z","iopub.execute_input":"2025-10-26T15:56:10.794528Z","iopub.status.idle":"2025-10-26T15:56:10.807277Z","shell.execute_reply.started":"2025-10-26T15:56:10.794486Z","shell.execute_reply":"2025-10-26T15:56:10.805946Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for col in malignant.columns:\n    print(col + ' missing values: ' + str(malignant[col].isna().sum()))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:10.809288Z","iopub.execute_input":"2025-10-26T15:56:10.809739Z","iopub.status.idle":"2025-10-26T15:56:10.819295Z","shell.execute_reply.started":"2025-10-26T15:56:10.809696Z","shell.execute_reply":"2025-10-26T15:56:10.818003Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#fill missing anatom site values with \"unknown or other\"\ntrain.anatom_site_general_challenge.fillna('other or unknown', inplace=True)\n\n#verify there are no more missing values in that column\nprint('anatom_site_general_challenge' + ' missing values: ' + str(train['anatom_site_general_challenge'].isna().sum()))\n\n#plot the new distribution\nax = sns.countplot(data=train, x='anatom_site_general_challenge')\n#train.anatom_site_general_challenge.hist()\nax.set_title('Distribution of Anatomical Sites Training Set')\nax.tick_params(axis='x', labelrotation = 45, labelsize = 12)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:10.820635Z","iopub.execute_input":"2025-10-26T15:56:10.820985Z","iopub.status.idle":"2025-10-26T15:56:11.037653Z","shell.execute_reply.started":"2025-10-26T15:56:10.820934Z","shell.execute_reply":"2025-10-26T15:56:11.036385Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **Test Set exploration**","metadata":{}},{"cell_type":"code","source":"test.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.03915Z","iopub.execute_input":"2025-10-26T15:56:11.039449Z","iopub.status.idle":"2025-10-26T15:56:11.052708Z","shell.execute_reply.started":"2025-10-26T15:56:11.039422Z","shell.execute_reply":"2025-10-26T15:56:11.051421Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.054042Z","iopub.execute_input":"2025-10-26T15:56:11.054386Z","iopub.status.idle":"2025-10-26T15:56:11.066329Z","shell.execute_reply.started":"2025-10-26T15:56:11.054355Z","shell.execute_reply":"2025-10-26T15:56:11.06521Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#print the number of missing values from each col in train\nfor col in test.columns:\n    print(col + ' missing values: ' + str(test[col].isna().sum()))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.067622Z","iopub.execute_input":"2025-10-26T15:56:11.068501Z","iopub.status.idle":"2025-10-26T15:56:11.082904Z","shell.execute_reply.started":"2025-10-26T15:56:11.068468Z","shell.execute_reply":"2025-10-26T15:56:11.081674Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#how many images are associated with each patient?\nindividuals_count = train.groupby('patient_id').count()\n\nindividuals_count.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.084284Z","iopub.execute_input":"2025-10-26T15:56:11.084639Z","iopub.status.idle":"2025-10-26T15:56:11.123314Z","shell.execute_reply.started":"2025-10-26T15:56:11.08461Z","shell.execute_reply":"2025-10-26T15:56:11.122256Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#show the disribution of image counts\nfig, ax = plt.subplots(figsize=(25,10))\nax = sns.histplot(data=individuals_count, x='image_name')\nax.set_title('Images per Patient')\nax.set_xlabel('Unique Images per Patient')\nax.set_ylabel('Number of Patients')\nax.set_xticks(ticks=range(0,120,10))\n\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.124704Z","iopub.execute_input":"2025-10-26T15:56:11.12516Z","iopub.status.idle":"2025-10-26T15:56:11.45163Z","shell.execute_reply.started":"2025-10-26T15:56:11.125129Z","shell.execute_reply":"2025-10-26T15:56:11.450334Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print('the mean number of images per patient is: {}'.format(round(individuals_count.image_name.mean(),2)))\nprint('the median number of images per patient is: {}'.format(round(individuals_count.image_name.median(),2)))\nprint('the standard deviation of the number of images per patient is: {}'.format(round(individuals_count.image_name.std(),2)))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.458395Z","iopub.execute_input":"2025-10-26T15:56:11.458729Z","iopub.status.idle":"2025-10-26T15:56:11.467464Z","shell.execute_reply.started":"2025-10-26T15:56:11.4587Z","shell.execute_reply":"2025-10-26T15:56:11.466206Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#check out the distribution of positive cases grouped by patient\nindividuals_sum = train.groupby('patient_id').sum()\n\nprint(individuals_sum.target.describe())\n\n#fig, ax = plt.subplots(figsize=(18,10))\nax = sns.histplot(data=individuals_sum, x='target', bins=10)\nax.set_title('Quantity of Malignant Tumors per Patient')\nax.set_xlabel('Sum of Positives')\nax.set_ylabel('Number of Patients')\n#ax.set_xticks(ticks=range(0,20))\n\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.468948Z","iopub.execute_input":"2025-10-26T15:56:11.46932Z","iopub.status.idle":"2025-10-26T15:56:11.721081Z","shell.execute_reply.started":"2025-10-26T15:56:11.469289Z","shell.execute_reply":"2025-10-26T15:56:11.719623Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**Another pass at missing sex and age values**","metadata":{}},{"cell_type":"code","source":"#let's pull out individuals from individuals_count who have fewer counts of sex or age_approx than image_name\nindividuals_count.loc[(individuals_count['sex'] < individuals_count['image_name']) | (individuals_count['age_approx'] < individuals_count['image_name'])]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.722458Z","iopub.execute_input":"2025-10-26T15:56:11.722794Z","iopub.status.idle":"2025-10-26T15:56:11.737792Z","shell.execute_reply.started":"2025-10-26T15:56:11.722764Z","shell.execute_reply":"2025-10-26T15:56:11.736569Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pats = ['IP_0550106','IP_5205991', 'IP_9835712']\nindividuals_sum.reset_index(inplace=True)\n\n\nindividuals_sum.query('patient_id in @pats')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.739429Z","iopub.execute_input":"2025-10-26T15:56:11.739878Z","iopub.status.idle":"2025-10-26T15:56:11.761417Z","shell.execute_reply.started":"2025-10-26T15:56:11.739835Z","shell.execute_reply":"2025-10-26T15:56:11.760108Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print('percentage of missing patient data= {}%'.format(round((3+48+17)/len(train)*100,2)))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.762903Z","iopub.execute_input":"2025-10-26T15:56:11.763301Z","iopub.status.idle":"2025-10-26T15:56:11.769603Z","shell.execute_reply.started":"2025-10-26T15:56:11.763268Z","shell.execute_reply":"2025-10-26T15:56:11.768428Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#drop all rows from the train dataframe that are associated with the 3 patients identified above.\ntrain.drop(train[(train['patient_id'] == 'IP_0550106') | (train['patient_id'] == 'IP_5205991') |(train['patient_id'] == 'IP_9835712')].index, inplace=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.771176Z","iopub.execute_input":"2025-10-26T15:56:11.771485Z","iopub.status.idle":"2025-10-26T15:56:11.793705Z","shell.execute_reply.started":"2025-10-26T15:56:11.771457Z","shell.execute_reply":"2025-10-26T15:56:11.792463Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#check for any more missing values:\nfor col in train.columns:\n    print(col + ' missing values: ' + str(train[col].isna().sum()))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.795149Z","iopub.execute_input":"2025-10-26T15:56:11.795496Z","iopub.status.idle":"2025-10-26T15:56:11.816835Z","shell.execute_reply.started":"2025-10-26T15:56:11.795465Z","shell.execute_reply":"2025-10-26T15:56:11.81554Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**Relationships between positive cases and other variables.**","metadata":{}},{"cell_type":"code","source":"#make sure index is the patient id so we can join these aggregate dfs\n\nindividuals_sum.set_index('patient_id', inplace=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.81829Z","iopub.execute_input":"2025-10-26T15:56:11.819117Z","iopub.status.idle":"2025-10-26T15:56:11.824884Z","shell.execute_reply.started":"2025-10-26T15:56:11.819074Z","shell.execute_reply":"2025-10-26T15:56:11.823685Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"patients = individuals_count.join(individuals_sum, lsuffix='_count', rsuffix='_sum')\npatients.drop(columns=['sex','age_approx_count','anatom_site_general_challenge','diagnosis', 'benign_malignant','target_count', 'age_approx_sum'], inplace=True)\npatients.rename(columns={'image_name':'n_images'}, inplace=True)\npatients.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.826329Z","iopub.execute_input":"2025-10-26T15:56:11.826744Z","iopub.status.idle":"2025-10-26T15:56:11.850524Z","shell.execute_reply.started":"2025-10-26T15:56:11.826703Z","shell.execute_reply":"2025-10-26T15:56:11.849285Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#join with train df to include sex and age data for each patient\npatients = patients.join(train.set_index('patient_id'), on='patient_id')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.852032Z","iopub.execute_input":"2025-10-26T15:56:11.852454Z","iopub.status.idle":"2025-10-26T15:56:11.879712Z","shell.execute_reply.started":"2025-10-26T15:56:11.852413Z","shell.execute_reply":"2025-10-26T15:56:11.878451Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#clean it up\npatients.reset_index(inplace=True)\npatients.drop_duplicates(subset='patient_id', inplace=True)\npatients.drop(columns=['image_name','anatom_site_general_challenge', 'diagnosis',   'benign_malignant', 'target'], inplace=True)\npatients.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.881129Z","iopub.execute_input":"2025-10-26T15:56:11.881552Z","iopub.status.idle":"2025-10-26T15:56:11.912022Z","shell.execute_reply.started":"2025-10-26T15:56:11.88151Z","shell.execute_reply":"2025-10-26T15:56:11.910861Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#plot n_images v. target_sum\nax1 = sns.scatterplot(data=patients, x='n_images', y ='target_sum', hue='sex')\nax1.set_title('n_images per patient v. target_sum')\n#ax1.tick_params(axis='x', labelrotation = 45, labelsize = 12)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:11.913373Z","iopub.execute_input":"2025-10-26T15:56:11.913703Z","iopub.status.idle":"2025-10-26T15:56:12.237622Z","shell.execute_reply.started":"2025-10-26T15:56:11.913674Z","shell.execute_reply":"2025-10-26T15:56:12.236426Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ax1 = sns.violinplot(data=patients, y='n_images', x ='target_sum')\nax1.set_title('n_images per patient v. target_sum')\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:12.238875Z","iopub.execute_input":"2025-10-26T15:56:12.239203Z","iopub.status.idle":"2025-10-26T15:56:12.513199Z","shell.execute_reply.started":"2025-10-26T15:56:12.239173Z","shell.execute_reply":"2025-10-26T15:56:12.51194Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ax1 = sns.stripplot(data=patients, y='target_sum', x ='sex')\nax1.set_title('target_sum distribution by gender')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:12.51479Z","iopub.execute_input":"2025-10-26T15:56:12.515139Z","iopub.status.idle":"2025-10-26T15:56:12.711476Z","shell.execute_reply.started":"2025-10-26T15:56:12.515107Z","shell.execute_reply":"2025-10-26T15:56:12.710284Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#plot age_approx v target_sum\nax1 = sns.stripplot(data=patients, x='age_approx', y ='target_sum')\nax1.set_title('age_approx v. target_sum')\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:12.712835Z","iopub.execute_input":"2025-10-26T15:56:12.713178Z","iopub.status.idle":"2025-10-26T15:56:13.065865Z","shell.execute_reply.started":"2025-10-26T15:56:12.713147Z","shell.execute_reply":"2025-10-26T15:56:13.064791Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#plot n_images v. target_sum\nax1 = sns.histplot(data=patients, x='age_approx', bins=16)\nax1.set_title('Ditribution of Patient Ages in Dataset')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:13.067073Z","iopub.execute_input":"2025-10-26T15:56:13.067351Z","iopub.status.idle":"2025-10-26T15:56:13.341074Z","shell.execute_reply.started":"2025-10-26T15:56:13.067326Z","shell.execute_reply":"2025-10-26T15:56:13.339934Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**Visualizing Images**\n","metadata":{}},{"cell_type":"code","source":"#open one image\n\n#import ImageIO\nimport imageio.v2 as imageio\n\n#load an image\nim = imageio.imread('../input/siim-isic-melanoma-classification/jpeg/train/ISIC_0015719.jpg')\n\n#plot image\nplt.imshow(im)\nplt.axis('off')\n#plt.show()\n\n#print metadata\nprint(im.meta.keys())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:13.342298Z","iopub.execute_input":"2025-10-26T15:56:13.342623Z","iopub.status.idle":"2025-10-26T15:56:17.352408Z","shell.execute_reply.started":"2025-10-26T15:56:13.342594Z","shell.execute_reply":"2025-10-26T15:56:17.351248Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"**Plot malignant lesions**","metadata":{}},{"cell_type":"code","source":"#Now, let's see if we can show all the malignant images\n\n#make a list of image names that have the malignant target value = 1\nmal_ims = train[train['target']==1].image_name\n\n#convert those image names into path names to access each photo\n#mal_im_paths = ['../input/siim-isic-melanoma-classification/jpeg/train/' + str(im) + '.jpg' for im in mal_ims]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:17.354025Z","iopub.execute_input":"2025-10-26T15:56:17.354429Z","iopub.status.idle":"2025-10-26T15:56:17.362606Z","shell.execute_reply.started":"2025-10-26T15:56:17.354391Z","shell.execute_reply":"2025-10-26T15:56:17.361255Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#plot all malignant images\n\nfig, axs = plt.subplots(nrows=146, ncols=4, tight_layout=True, figsize=(15,365))\nfig.suptitle('Malignant Lesions', fontsize=14)\n\nfor ax, image in zip(axs.ravel(), mal_ims):\n    path = '../input/siim-isic-melanoma-classification/jpeg/train/' + str(image) + '.jpg'\n    im = imageio.imread(path)\n    ax.imshow(im)\n    ax.axis('off')\n    ax.set_title(image)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T15:56:17.363749Z","iopub.execute_input":"2025-10-26T15:56:17.364107Z","iopub.status.idle":"2025-10-26T16:06:03.733898Z","shell.execute_reply.started":"2025-10-26T15:56:17.364075Z","shell.execute_reply":"2025-10-26T16:06:03.732204Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import random\nrandom.seed(42)\n\n#make a list of image names that have the malignant target value = 0\nben_ims = train[train['target']==0].image_name\n\n#take a random sample of 100 of these images\nrand_ben_ims = random.sample(list(ben_ims),100)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T16:06:03.735919Z","iopub.execute_input":"2025-10-26T16:06:03.736775Z","iopub.status.idle":"2025-10-26T16:06:03.757087Z","shell.execute_reply.started":"2025-10-26T16:06:03.736722Z","shell.execute_reply":"2025-10-26T16:06:03.755635Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#plot the subset of 100 benign images\n\nfig, axs = plt.subplots(nrows=25, ncols=4, tight_layout=True, figsize=(15,62.5))\nfig.suptitle('Subset of Benign Lesions', fontsize=14, y=0.98)\n\nfor ax, image in zip(axs.ravel(), rand_ben_ims):\n    path = '../input/siim-isic-melanoma-classification/jpeg/train/' + str(image) + '.jpg'\n    im = imageio.imread(path)\n    ax.imshow(im)\n    ax.axis('off')\n    ax.set_title(image)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T16:06:03.759032Z","iopub.execute_input":"2025-10-26T16:06:03.759399Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# System\nimport cv2\nimport os, os.path\nfrom PIL import Image             \nimport gc\nimport time\nimport datetime\n\n# Basics\nimport pandas as pd\nimport numpy as np\nimport random\nimport seaborn as sns\nimport matplotlib\nimport matplotlib.pyplot as plt\n%matplotlib inline\n\nfrom tqdm.notebook import tqdm     \n\n# SKlearn\nfrom sklearn.model_selection import StratifiedKFold, GroupKFold\nfrom sklearn.metrics import accuracy_score, roc_auc_score, confusion_matrix\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.preprocessing import OneHotEncoder\nfrom sklearn import preprocessing\n\nfrom skimage import io\n\n# PyTorch\nimport torch\nimport torchvision\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom torch.utils.data import Dataset, DataLoader, Subset\n\nfrom torchvision.models import resnet34\nfrom torchvision import transforms\n\nimport warnings\nwarnings.filterwarnings(\"ignore\")\n\nprint(\"PyTorch Version: \",torch.__version__)\nprint(\"Torchvision Version: \",torchvision.__version__)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# For reproducibility\nseed = 1234\n\nnp.random.seed(seed)\nrandom.seed(seed)\ntorch.manual_seed(seed)\ntorch.cuda.manual_seed(seed)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\nprint('Device available now:', device)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')[1:1000]\n# train_df = train_df.head(1000)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df.target.value_counts()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(train_df)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class MelanomaDataset(Dataset):\n    \n    def __init__(self, dataframe,is_train=True, is_valid=False, is_test=False):\n        self.dataframe, self.is_train, self.is_valid = dataframe, is_train, is_valid\n        \n        # Data Augmentation\n        if is_train or is_test:\n            self.transform = transforms.Compose([transforms.ToPILImage(),\n                                                 transforms.RandomResizedCrop((224,224), scale=(0.4, 1.0)),\n                                                 transforms.RandomHorizontalFlip(p = 0.3),\n                                                 transforms.RandomVerticalFlip(p = 0.3),\n                                                 transforms.ToTensor(),\n                                                 transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))])\n        else:\n            self.transform = transforms.Compose([transforms.ToPILImage(),\n                                                 transforms.Resize((224,224)),\n                                                 transforms.ToTensor(),\n                                                 transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))])\n            \n    def __len__(self):\n        return len(self.dataframe)\n    \n    def __getitem__(self, index):\n        # Select path and read image\n        img_name = self.dataframe['image_name'][index]\n        image_path = f'../input/siim-isic-melanoma-classification/jpeg/train/{img_name}.jpg'\n        image = io.imread(image_path)\n        \n        # Apply transforms\n        image = self.transform(image)\n\n        \n        # If train/valid: image + class | If test: only image\n        if self.is_train or self.is_valid:\n            return (image, self.dataframe['target'][index])\n        else:\n            return (image)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(resnet34(pretrained=True))","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class ResNet34Network(nn.Module):\n    def __init__(self):\n        super().__init__()\n        \n        # Define Feature part (IMAGE)\n        self.features = resnet34(pretrained=True) # 1000 neurons out\n        \n        for param in self.features.parameters():\n            param.requires_grad = False\n  \n        # Define Classification part\n        self.classification = nn.Linear(1000, 1)\n        \n        \n    def forward(self, image):\n        # Image CNN\n        image = self.features(image)\n        \n        # Classifier\n        out = self.classification(image)\n        \n        return out","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = ResNet34Network()\nmodel = model.to(device)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(model)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Data object and Loader\ndataset = MelanomaDataset(train_df, is_train=True, is_valid=False, is_test=False)\nloader = DataLoader(dataset,batch_size=3, shuffle=True)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Get a sample\nfor image, labels in loader:\n    image_example = image\n    labels_example = torch.tensor(labels, dtype=torch.float32)\n    break\n    \nprint('Data shape:', image_example.shape)\nprint('Label:', labels_example)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"learning_rate = 0.0005\nepochs = 5\ndevice = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\nprint(device)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Initiate the model\nmodel = model\nmodel = model.to(device)\noptimizer = torch.optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), lr = learning_rate)\ncriterion = nn.BCEWithLogitsLoss()  ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_size = int(len(train_df) * 0.6)\nval_size = int(len(train_df) * 0.2)\ntest_size = int(len(train_df) * 0.2)\n\nprint(f'train size : {train_size}, val size : {val_size}, test size : {test_size}')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# --- Read in Data ---\ntrain_data = train_df.iloc[:train_size].reset_index(drop=True)\nvalid_data = train_df.iloc[train_size:train_size + val_size].reset_index(drop=True)\ntest_data = train_df.iloc[train_size + val_size:].reset_index(drop=True)\n# Create Data instances\ntrain = MelanomaDataset(train_data, is_train=True, is_valid=False, is_test=False)\nvalid = MelanomaDataset(valid_data, is_train=False, is_valid=True, is_test=False)\ntest = MelanomaDataset(valid_data, is_train=False, is_valid=True, is_test=False)\n\n# Dataloaders\ntrain_loader = DataLoader(train, batch_size=16, shuffle=True)\nvalid_loader = DataLoader(valid, batch_size=8, shuffle=True)\ntest_loader = DataLoader(valid, batch_size=1, shuffle=True)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def check_accuracy(loader, model):\n    num_correct = 0\n    num_samples = 0\n    model.eval()\n    \n    with torch.no_grad():\n        for x, y in loader:\n            x = x.to(device=device)\n            y = y.to(device=device)\n            \n            scores = model(x)\n            _, predictions = scores.max(1)\n            num_correct += (predictions == y).sum()\n            num_samples += predictions.size(0)\n        \n        print(f'Got {num_correct} / {num_samples} with Test Accuracy {float(num_correct)/float(num_samples)*100:.2f}') ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"check_accuracy(test_loader,model)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **Building CNN Sequential Model**","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf \nimport tensorflow_addons as tfa \nimport numpy as np \nimport pandas as pd \nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_img_dir = '../input/siim-isic-melanoma-classification/jpeg/train/'\ntest_img_dir = '../input/siim-isic-melanoma-classification/jpeg/test/'\ntrain = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')\ntest = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')\ntrain1= pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')[1:1000]\ntest1 = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# === EPOCHS ===\nfor epoch in range(epochs):\n    print(f'epoch : {epoch} start!')\n    start_time = time.time()\n    correct = 0\n    train_losses = 0\n\n    # === TRAIN ===\n    # Sets the module in training mode.\n    model.train()\n\n    for images, labels in train_loader:\n        # Save them to device\n        images = torch.tensor(images, device=device, dtype=torch.float32)\n        labels = torch.tensor(labels, device=device, dtype=torch.float32)\n\n        # Clear gradients first; very important, usually done BEFORE prediction\n        optimizer.zero_grad()\n\n        # Log Probabilities & Backpropagation\n        out = model(images)\n        loss = criterion(out, labels.unsqueeze(1))\n        loss.backward()\n        optimizer.step()\n\n        train_losses += loss.item()\n        # From log probabilities to actual probabilities\n        train_preds = torch.round(torch.sigmoid(out)) # 0 and 1\n        # Number of correct predictions\n        correct += (train_preds.cpu() == labels.cpu().unsqueeze(1)).sum().item()\n\n    # Compute Train Accuracy\n    train_acc = correct*100 / train_size\n    print(f'Epoch :{epoch + 1} - train accuracy: {train_acc}')\n    \n    # === EVAL ===\n    model.eval()\n\n    # Create matrix to store evaluation predictions (for accuracy)\n    valid_preds = torch.zeros(size = (len(valid_data), 1), device=device, dtype=torch.float32)\n\n\n    # Disables gradients (we need to be sure no optimization happens)\n    with torch.no_grad():\n        for k, (images, labels) in enumerate(valid_loader):\n            images = torch.tensor(images, device=device, dtype=torch.float32)\n            labels = torch.tensor(labels, device=device, dtype=torch.float32)\n\n            out = model(images)\n            pred = torch.sigmoid(out)\n            valid_preds[k*images.shape[0] : k*images.shape[0] + images.shape[0]] = pred\n\n        # Compute accuracy\n        valid_acc = accuracy_score(valid_data['target'].values, \n                                           torch.round(valid_preds.cpu()))*100\n        \n        # Compute ROC\n        valid_roc = roc_auc_score(valid_data['target'].values, \n                                          valid_preds.cpu())\n\n        # Compute time on Train + Eval\n        duration = str(datetime.timedelta(seconds=time.time() - start_time))[:7]\n\n\n        # PRINT INFO\n        print('{} | Epoch: {}/{} | Loss: {:.4} | Train Acc: {:.3} | Valid Acc: {:.3} ROC: {:.3}'.\\\n                    format(duration, epoch+1, epochs, train_losses, train_acc, valid_acc,valid_roc))\n        \n        \ntorch.save(model.state_dict(), './model.pt')\n\nfrom IPython.display import FileLink\nFileLink(r'model.pt')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train.target.value_counts()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train1.target.value_counts()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# loading the data\ntrain_car = []\nfor image_name in train1.image_name:\n    train_car.append(tf.keras.preprocessing.image.img_to_array(\n        tf.keras.preprocessing.image.load_img(path = (train_img_dir + image_name + \".jpg\"), color_mode = \"rgba\", target_size = (128,128)), dtype=\"float32\")\n                    )","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train1[\"img\"] = train_car\ntest[\"path\"] = [(test_img_dir + img_name + \".jpg\") for img_name in test.image_name]","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# split the data\nx_train, x_cross_validation, y_train, y_cross_validation = train_test_split(train1.img, train1.target, test_size=0.2, shuffle = True, random_state=42)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# scale the pixels between 0 and 1\nx_train /= 255\nx_cross_validation /= 255\n# redefine dtypes\ny_train = np.array(y_train, dtype = \"float32\")\ny_cross_validation = np.array(y_cross_validation, dtype = \"float32\")\nx_train = np.array([np.array(val) for val in x_train])\nx_cross_validation = np.array([np.array(val) for val in x_cross_validation])","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model1 = tf.keras.models.Sequential()\n\n# Convolutional & Max Pooling layers\n\nmodel1.add(tf.keras.layers.Conv2D(16, kernel_size=(3, 3), activation='relu', input_shape=(128,128,4)))\nmodel1.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2)))\n\nmodel1.add(tf.keras.layers.Conv2D(64, kernel_size=(3, 3), activation='relu'))\nmodel1.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2)))\n\nmodel1.add(tf.keras.layers.Conv2D(128, kernel_size=(3, 3), activation='relu'))\nmodel1.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2)))\n\n# Flatten & Dense layers\n\nmodel1.add(tf.keras.layers.Flatten())\nmodel1.add(tf.keras.layers.Dense(512, activation='relu'))\n\n# performing binary classification\nmodel1.add(tf.keras.layers.Dense(1, activation='sigmoid'))\n\nmodel1.compile(loss = tfa.losses.SigmoidFocalCrossEntropy(),\n              optimizer = tf.keras.optimizers.Adam(),\n              metrics = ['binary_accuracy',\n                       tf.keras.metrics.FalsePositives(),\n                       tf.keras.metrics.FalseNegatives(), \n                       tf.keras.metrics.TruePositives(),\n                       tf.keras.metrics.TrueNegatives()\n                      ]\n             )","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model1.summary()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.optimizers import Adam\n\nlearning_rate = .0001\noptimizer = Adam(learning_rate=learning_rate)\n\nmodel1.compile(loss=\"binary_crossentropy\", optimizer=optimizer, metrics=['accuracy'])","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# saving the best model for our predictions\ncheckpointer = tf.keras.callbacks.ModelCheckpoint(filepath=\"weights.hdf5\", verbose=1, save_best_only=True)\n\nhistory = model1.fit(x = x_train,\n                    y = y_train,\n                    validation_data=(x_cross_validation, y_cross_validation),\n                    batch_size=10,\n                    epochs=10,\n                    verbose=1, \n                    callbacks=[checkpointer]\n                   )","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# summarize history for accuracy\nplt.plot(history.history['accuracy'])\nplt.plot(history.history['val_accuracy'])\nplt.title('CNN Model Accuracy')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train accuracy', ' Validation accuracy'], loc='upper left')\nplt.show()\n# summarize history for loss\nplt.plot(history.history['loss'])\nplt.plot(history.history['val_loss'])\nplt.title('CNN Model Loss')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.legend(['train loss', 'test loss'], loc='upper left')\nplt.show()\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# input to be predicted\ntest = tf.keras.preprocessing.image.img_to_array(tf.keras.preprocessing.image.load_img(path = (\"../input/siim-isic-melanoma-classification/jpeg/test/ISIC_0052060.jpg\"), color_mode = \"rgba\", target_size = (128,128)), dtype=\"float32\")\ntest = test / 255\ntest=np.reshape(test,(1,128,128,4))\ntest = np.array(test)\n# load the best model\nmodel1.load_weights('weights.hdf5')\n\nmodel1.predict(test)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model1.compile(optimizer='Adam',\n              loss='categorical_crossentropy',\n              metrics=['accuracy'])","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"score = model1.evaluate(x_cross_validation, y_cross_validation, verbose=0)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print('Test loss:', score[0])\nprint('Test accuracy:', score[1])","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **Building ResNet18**","metadata":{}},{"cell_type":"code","source":"\nfrom torchvision.models import resnet18\nfrom torchvision import transforms\n\nimport warnings\nwarnings.filterwarnings(\"ignore\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(resnet18(pretrained=True))","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class ResNet18Network(nn.Module):\n    def __init__(self):\n        super().__init__()\n        \n        # Define Feature part (IMAGE)\n        self.features = resnet18(pretrained=True) # 1000 neurons out\n        \n        for param in self.features.parameters():\n            param.requires_grad = False\n  \n        # Define Classification part\n        self.classification = nn.Linear(1000, 1)\n        \n        \n    def forward(self, image):\n        # Image CNN\n        image = self.features(image)\n        \n        # Classifier\n        out = self.classification(image)\n        \n        return out","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model5 = ResNet18Network()\nmodel5 = model5.to(device)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model5 = model5\nmodel5 = model5.to(device)\noptimizer = torch.optim.Adam(filter(lambda p: p.requires_grad, model5.parameters()), lr = learning_rate)\ncriterion = nn.BCEWithLogitsLoss() ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# === EPOCHS ===\nfor epoch in range(epochs):\n    print(f'epoch : {epoch} start!')\n    start_time = time.time()\n    correct = 0\n    train_losses = 0\n\n    # === TRAIN ===\n    # Sets the module in training mode.\n    model5.train()\n\n    for images, labels in train_loader:\n        # Save them to device\n        images = torch.tensor(images, device=device, dtype=torch.float32)\n        labels = torch.tensor(labels, device=device, dtype=torch.float32)\n\n        # Clear gradients first; very important, usually done BEFORE prediction\n        optimizer.zero_grad()\n\n        # Log Probabilities & Backpropagation\n        out = model(images)\n        loss = criterion(out, labels.unsqueeze(1))\n        loss.backward()\n        optimizer.step()\n\n        train_losses += loss.item()\n        # From log probabilities to actual probabilities\n        train_preds = torch.round(torch.sigmoid(out)) # 0 and 1\n        # Number of correct predictions\n        correct += (train_preds.cpu() == labels.cpu().unsqueeze(1)).sum().item()\n\n    # Compute Train Accuracy\n    train_acc = correct*100 / train_size\n    print(f'Epoch :{epoch + 1} - train accuracy: {train_acc}')\n    \n    # === EVAL ===\n    model5.eval()\n\n    # Create matrix to store evaluation predictions (for accuracy)\n    valid_preds = torch.zeros(size = (len(valid_data), 1), device=device, dtype=torch.float32)\n\n\n    # Disables gradients (we need to be sure no optimization happens)\n    with torch.no_grad():\n        for k, (images, labels) in enumerate(valid_loader):\n            images = torch.tensor(images, device=device, dtype=torch.float32)\n            labels = torch.tensor(labels, device=device, dtype=torch.float32)\n\n            out = model5(images)\n            pred = torch.sigmoid(out)\n            valid_preds[k*images.shape[0] : k*images.shape[0] + images.shape[0]] = pred\n\n        # Compute accuracy\n        valid_acc = accuracy_score(valid_data['target'].values, \n                                           torch.round(valid_preds.cpu()))*100\n        \n        # Compute ROC\n        valid_roc = roc_auc_score(valid_data['target'].values, \n                                          valid_preds.cpu())\n\n        # Compute time on Train + Eval\n        duration = str(datetime.timedelta(seconds=time.time() - start_time))[:7]\n\n\n        # PRINT INFO\n        print('{} | Epoch: {}/{} | Loss: {:.4} | Train Acc: {:.3} | Valid Acc: {:.3} ROC: {:.3}'.\\\n                    format(duration, epoch+1, epochs, train_losses, train_acc, valid_acc,valid_roc))\n        \n        \ntorch.save(model5.state_dict(), './model5.pt')\n\nfrom IPython.display import FileLink\nFileLink(r'model5.pt')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def check_accuracy(loader, model5):\n    num_correct = 0\n    num_samples = 0\n    model5.eval()\n    \n    with torch.no_grad():\n        for x, y in loader:\n            x = x.to(device=device)\n            y = y.to(device=device)\n            \n            scores = model5(x)\n            _, predictions = scores.max(1)\n            num_correct += (predictions == y).sum()\n            num_samples += predictions.size(0)\n        \n        print(f'Got {num_correct} / {num_samples} with Test Accuracy {float(num_correct)/float(num_samples)*100:.2f}')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"check_accuracy(test_loader,model5)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **Implemantation of VGG16**","metadata":{}},{"cell_type":"code","source":"import keras,os\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Conv2D, MaxPool2D , Flatten\nfrom keras.preprocessing.image import ImageDataGenerator\nimport numpy as np","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model3 = Sequential()\nmodel3.add(Conv2D(input_shape=(224,224,3),filters=64,kernel_size=(3,3),padding=\"same\", activation=\"relu\"))\nmodel3.add(Conv2D(filters=64,kernel_size=(3,3),padding=\"same\", activation=\"relu\"))\nmodel3.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))\nmodel3.add(Conv2D(filters=128, kernel_size=(3,3), padding=\"same\", activation=\"relu\"))\nmodel3.add(Conv2D(filters=128, kernel_size=(3,3), padding=\"same\", activation=\"relu\"))\nmodel3.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))\nmodel3.add(Conv2D(filters=256, kernel_size=(3,3), padding=\"same\", activation=\"relu\"))\nmodel3.add(Conv2D(filters=256, kernel_size=(3,3), padding=\"same\", activation=\"relu\"))\nmodel3.add(Conv2D(filters=256, kernel_size=(3,3), padding=\"same\", activation=\"relu\"))\nmodel3.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))\nmodel3.add(Conv2D(filters=512, kernel_size=(3,3), padding=\"same\", activation=\"relu\"))\nmodel3.add(Conv2D(filters=512, kernel_size=(3,3), padding=\"same\", activation=\"relu\"))\nmodel3.add(Conv2D(filters=512, kernel_size=(3,3), padding=\"same\", activation=\"relu\"))\nmodel3.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))\nmodel3.add(Conv2D(filters=512, kernel_size=(3,3), padding=\"same\", activation=\"relu\"))\nmodel3.add(Conv2D(filters=512, kernel_size=(3,3), padding=\"same\", activation=\"relu\"))\nmodel3.add(Conv2D(filters=512, kernel_size=(3,3), padding=\"same\", activation=\"relu\"))\nmodel3.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model3.add(Flatten())\nmodel3.add(Dense(units=4096,activation=\"relu\"))\nmodel3.add(Dense(units=4096,activation=\"relu\"))\nmodel3.add(Dense(units=2, activation=\"softmax\"))","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.optimizers import Adam\nopt = Adam(lr=0.001)\nmodel3.compile(optimizer=opt, loss=keras.losses.categorical_crossentropy, metrics=['accuracy'])","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model3.summary()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.callbacks import ModelCheckpoint, EarlyStopping\ncheckpoint = ModelCheckpoint(\"vgg16_1.h5\", monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)\nearly = EarlyStopping(monitor='val_acc', min_delta=0, patience=20, verbose=1, mode='auto')\nhistory = model3.fit(x = x_train,\n                    y = y_train,\n                    validation_data=(x_cross_validation, y_cross_validation),\n                    batch_size=50,\n                    epochs=50,\n                    verbose=1, \n                    callbacks=[checkpointer]\n                   )","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport os,cv2\nfrom IPython.display import Image\nfrom keras.preprocessing import image\nfrom keras import optimizers\nfrom keras import layers,models\nfrom keras.applications.imagenet_utils import preprocess_input\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom keras import regularizers\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.applications.vgg16 import VGG16","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_img_dir = '../input/siim-isic-melanoma-classification/jpeg/train/'\ntest_img_dir = '../input/siim-isic-melanoma-classification/jpeg/test/'\ntrain = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')\ntest = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')\ntrain1= pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')[1:1000]\ntest1 = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train1.target.value_counts()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train1['target'] = train1['target'].astype(str)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen=ImageDataGenerator(rescale=1./255)\nbatch_size=50","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_generator=datagen.flow_from_dataframe(dataframe=train1[:901],directory=train_img_dir,x_col= 'image_name',\n                                            y_col='target',class_mode='raw',batch_size=batch_size,\n                                            target_size=(224,224))\n\n\nvalidation_generator=datagen.flow_from_dataframe(dataframe=train1[900:],directory=train_img_dir,x_col= 'image_name',\n                                                y_col='target',class_mode='raw',batch_size=10,\n                                                target_size=(224,224))","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **Building MobileNet** ","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.applications.mobilenet import MobileNet\nfrom keras.layers import Dense, GlobalAveragePooling2D,Activation,Flatten\nmodel4 = tf.keras.applications.MobileNet()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model4.summary()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"X=train1.drop('target',axis=1)\ny=train1['target']","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from imblearn.over_sampling import RandomOverSampler\nros = RandomOverSampler(random_state=42)\nX_res, y_res = ros.fit_resample(X, y)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#mix X_res and y_res into train dataset again\nX_res['target']=y_res\ntrain_resampled=X_res","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}