From bafb8c8ac2b68a8cfab28c49f4632e0c7b3141e6 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sun, 3 Jan 2021 01:15:02 +0530 Subject: [PATCH 01/49] Update interview_prep.md --- interview_prep.md | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/interview_prep.md b/interview_prep.md index 7fb89e6..13f11d3 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -2,3 +2,36 @@ When two or more predictors are highly correlated to each other such that one predictor can be derived using the linear combinations of other predictors, then the predictors are said to be collinear + +### 2. What is the difference between standardisation and normalization ? Why is it useful? +### 3. What is the central limit theorem ? Why is it useful ? +### 4. What is the inter quartile range ? Why is it useful ? +### 5. What is the difference between t-test and z-test ? Why is it useful ? +### 6. Why do we take n-1 when calculating sample variance? Why is it useful ? +Read about Besel correction +### 7. What are the assumptions of the normal distribution ? Why is it useful ? +### 8. What are the different approches to outlier detection ? How will you handle the outliers? Why is it useful ? +### 9. Where is RMSE a bad case ? How do we solve this ? +### 10. What are the loss functions used in logistic regression ? +log loss function +### 11. Explain random forest in laymen terms ? +### 12. How does logisitc regression work in laymen terms ? +### 13. Why is logistic regression bad idea for multiclass classification ? +### 14. How do you perform the train test split in a timeseries modelling ? +### 15. What is the impact on timeseries model in case we have latge variation in data ? +### 16. How do you decide the value of K(value of clusters) in K-means clustering ? +### 17. What are the advantages and disadvantages of undersampling and oversampling ? +### 18. Which are some supervised algorithms that are not impacted by imbalanced data ? +### 19. You are a placement coordinator, you have to design a system for resume recommendation aligning to a company's requirement ? +a. K means clustering to make clusters +b. Ranking algorithm to sort for relevance + +_Second Strategy_ + +a. Perform document similarity using Hamming distance (distance based approach) +b. Compute the JD document distance with the resumes +c. Shortlist top K resumes + +### 20. How will you encode a feature like PinCode which has very high number of discrete values? +Target mean encoding +### 21. How do you design the architecture of a neural network? From bf98e117fae13abeecfae4a12f3eb0f0a5150dd2 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sun, 3 Jan 2021 11:53:41 +0530 Subject: [PATCH 02/49] Update interview_prep.md --- interview_prep.md | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/interview_prep.md b/interview_prep.md index 13f11d3..3a5b1aa 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -35,3 +35,24 @@ c. Shortlist top K resumes ### 20. How will you encode a feature like PinCode which has very high number of discrete values? Target mean encoding ### 21. How do you design the architecture of a neural network? + +## Section II + +| Algorithm | Problem Identification | Evaluation Metric | Bias Variance | Impact of outliers | Impact of imbalanced data | | +|-------------------------|------------------------|-------------------------------------------------------------------------------------------------|---------------|--------------------|---------------------------|---| +| Linear Regression | Regression | - Coefficient of determination (R2) - Adjusted R2 - Root Mean Square Error (RMSE) - Mean Absolute Error (MAE) - Root Mean Squared Logarithmic Error (RMSLE)| - High Bias Low Variance | -Impacted by outliers | | | +| Logistic Regression | Classification | - Accuracy - Precision - Recall - F-beta score - Area under ROC curve | - High Bias Low Variance | -Impacted by outliers | | | +| Support Vector Machines | Classification | - Accuracy - Precision - Recall - F-beta score - Area under ROC curve | - Low Bias High Variance | Sensitive to outliers | Sensitive to imbalanced data | | +| K-nearest neighbors | Classification | - Accuracy - Precision - Recall - F-beta score - Area under ROC curve | - Low Bias High Variance | Sensitive to outliers | Sensitive to imbalanced data | | +| Decision Tree | Both | Both | - Low Bias High Variance | - Not impacted by outliers | - Not impacted by imbalanced data | | +| Random Forest | Both | Both | - Low Bias High Variance | - Not impacted by outliers | - Not impacted by imbalanced data | | +| K-means clustering | Clustering | - Elbow method - Silhoutte Analysis | | | | | +| | | | | | | | + +### 22. Why do CNNs perfom better with images ? (What is it that CNN achieve better than ANN when delaing with image data) +### 23. Explain K-means clustering in laymen terms ? +### 24. What is the evaluation metric for K-means clustering ? +### 25. What is the impact of outliers on K-means clustering ? +### 26. What is the impact of outliers on K-nearest neigbors ? +### 25. What is the impact of imbalanced data on K-means clustering ? +### 26. What is the impact of imbalanced data on K-nearest neigbors ? From 9f1cf005b9936393c18a42243709041188c788c9 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sun, 3 Jan 2021 11:56:27 +0530 Subject: [PATCH 03/49] Update interview_prep.md --- interview_prep.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/interview_prep.md b/interview_prep.md index 3a5b1aa..768e81e 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -46,7 +46,7 @@ Target mean encoding | K-nearest neighbors | Classification | - Accuracy - Precision - Recall - F-beta score - Area under ROC curve | - Low Bias High Variance | Sensitive to outliers | Sensitive to imbalanced data | | | Decision Tree | Both | Both | - Low Bias High Variance | - Not impacted by outliers | - Not impacted by imbalanced data | | | Random Forest | Both | Both | - Low Bias High Variance | - Not impacted by outliers | - Not impacted by imbalanced data | | -| K-means clustering | Clustering | - Elbow method - Silhoutte Analysis | | | | | +| K-means clustering | Clustering | - Elbow method - Silhoutte Analysis | | Senstive to Outliers | | | | | | | | | | | ### 22. Why do CNNs perfom better with images ? (What is it that CNN achieve better than ANN when delaing with image data) From f99e3bc7344614065bd8cbcfecc4461673939510 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sun, 3 Jan 2021 12:14:42 +0530 Subject: [PATCH 04/49] Update interview_prep.md --- interview_prep.md | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/interview_prep.md b/interview_prep.md index 768e81e..809a5a8 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -51,8 +51,9 @@ Target mean encoding ### 22. Why do CNNs perfom better with images ? (What is it that CNN achieve better than ANN when delaing with image data) ### 23. Explain K-means clustering in laymen terms ? -### 24. What is the evaluation metric for K-means clustering ? -### 25. What is the impact of outliers on K-means clustering ? -### 26. What is the impact of outliers on K-nearest neigbors ? -### 25. What is the impact of imbalanced data on K-means clustering ? -### 26. What is the impact of imbalanced data on K-nearest neigbors ? +### 24. Does a low coefficient of determination always mean that my model is bad or vice versa ? Explain. +* R-squared does not measure goodness of fit. +* R-squared does not measure predictive error. +* R-squared does not allow you to compare models using transformed responses. +* R-squared does not measure how one variable explains another. +Ref:- https://data.library.virginia.edu/is-r-squared-useless/#:~:text=Let's%20recap%3A-,R%2Dsquared%20does%20not%20measure%20goodness%20of%20fit.,how%20one%20variable%20explains%20another. From 2a2d03a1d4385976fe83b3b4649ee4d342893406 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sun, 3 Jan 2021 12:15:29 +0530 Subject: [PATCH 05/49] Update interview_prep.md --- interview_prep.md | 1 + 1 file changed, 1 insertion(+) diff --git a/interview_prep.md b/interview_prep.md index 809a5a8..0105f8a 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -56,4 +56,5 @@ Target mean encoding * R-squared does not measure predictive error. * R-squared does not allow you to compare models using transformed responses. * R-squared does not measure how one variable explains another. + Ref:- https://data.library.virginia.edu/is-r-squared-useless/#:~:text=Let's%20recap%3A-,R%2Dsquared%20does%20not%20measure%20goodness%20of%20fit.,how%20one%20variable%20explains%20another. From 2bec118e2b9ba09c3d5f2ba967446f8d99321ef3 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sun, 3 Jan 2021 12:36:07 +0530 Subject: [PATCH 06/49] Update interview_prep.md --- interview_prep.md | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/interview_prep.md b/interview_prep.md index 0105f8a..8e04c44 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -58,3 +58,22 @@ Target mean encoding * R-squared does not measure how one variable explains another. Ref:- https://data.library.virginia.edu/is-r-squared-useless/#:~:text=Let's%20recap%3A-,R%2Dsquared%20does%20not%20measure%20goodness%20of%20fit.,how%20one%20variable%20explains%20another. + +### 24. What is the difference between probability and likelihood ? +### 25. What is the difference between generative and discriminative models ? +### 26. How is a decision tree pruned ? +### 27. What do you understand by the bias variance tradeoff ? + +![](https://djsaunde.files.wordpress.com/2017/07/bias-variance-tradeoff.png) + +Bias ia how well the model fits the data. Variance tells us the magnitude of change in the model based on the change in data +a. Very simple models have high bias and low variance eg. linear models +b. Very complex models have low bias and high variance eg. tree based models. Hence they are more prone to overfitting. + +How to deal with them ? + +| High Bias | High Variance | | +|----------------------------------------------|---------------|---| +| Try getting additional features | Try getting more training examples | | +| Try adding polynomial features | Try smaller set of features | | +| Try to decrease the regularization parameter | Try to increase the regularization parameter | | From 643cce532982290bad9eb603cff9747850dc7340 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sun, 3 Jan 2021 12:57:26 +0530 Subject: [PATCH 07/49] Update interview_prep.md --- interview_prep.md | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/interview_prep.md b/interview_prep.md index 8e04c44..a16d333 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -4,6 +4,17 @@ When two or more predictors are highly correlated to each other such that one pr can be derived using the linear combinations of other predictors, then the predictors are said to be collinear ### 2. What is the difference between standardisation and normalization ? Why is it useful? +Standardisation is a scclaing technique in which values are shifted and rescaled so that the mean is 0 and the variance is 1 + +Normalization is a scaling technique in which values are shifted and rescaled so that they end up ranging between 0 and 1. It is also known as Min-Max scaling + +* Algorithms which use gradient descent based optimisation (linear regression, logistic regression, neural networks) will require features to be scaled so that optimization will be faster and the convergence will be more accurate. +* **Having features on a similar scale can help the gradient descent converge more quickly towards the minima.** +* Distance algorithms like KNN, K-means, and SVM are most affected by the range of features. This is because behind the scenes they are using distances between data points to determine their similarity. +* **Therefore, we scale our data before employing a distance based algorithm so that all the features contribute equally to the result.** + +![](https://i.pinimg.com/originals/1c/16/04/1c160466f8bfd26ca66a44f79514fb5d.jpg) + ### 3. What is the central limit theorem ? Why is it useful ? ### 4. What is the inter quartile range ? Why is it useful ? ### 5. What is the difference between t-test and z-test ? Why is it useful ? From 7f065d665abff80a285763dc5ae08ed1cb945a1d Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sun, 3 Jan 2021 13:05:25 +0530 Subject: [PATCH 08/49] Update interview_prep.md --- interview_prep.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/interview_prep.md b/interview_prep.md index a16d333..ba84d0c 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -16,6 +16,16 @@ Normalization is a scaling technique in which values are shifted and rescaled so ![](https://i.pinimg.com/originals/1c/16/04/1c160466f8bfd26ca66a44f79514fb5d.jpg) ### 3. What is the central limit theorem ? Why is it useful ? +The Central Limit Theorem is about how the sum of many different independent random variables tends towards a normal distribution (bell curve). + +For example: suppose you're rolling 2 6-sided dice. The rolls are all independent because one of the rolls doesn't affect any of the other rolls. For a single die, the distribution is the same chance for 1 2 3 4 5 and 6. + +But of you add the sum of 2 dice, you will notice that you have a 1/36 chance to get a 2, 2/36 chance to get a 3, 3/36 chance to get a 4, ..., up until 6/36 chance of getting a 7, then the chance decreases again until you're back at 1/36 chance of getting a 12. This is because the values in the middle, like 7, can be reached by getting 1+6, 6+1, 2+5, 5+2, 3+4 and 4+3, whereas the edges like 2 require a single very specific result (1+1) where every single die needs to land on 1. + +If you further increase the number of dice you roll, the edge cases become less and less likely, because they keep requiring very specific results, whereas the results in the middle become more likely. The more dice you add, the more it will eventually look like a bell curve. + +![](https://prwatech.in/blog/wp-content/uploads/2019/06/CetralLimitThm-1024x512.png) + ### 4. What is the inter quartile range ? Why is it useful ? ### 5. What is the difference between t-test and z-test ? Why is it useful ? ### 6. Why do we take n-1 when calculating sample variance? Why is it useful ? From a59d0b18778b1790e29cf4a70ff4b5ad3dcca781 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sun, 3 Jan 2021 13:49:52 +0530 Subject: [PATCH 09/49] Update interview_prep.md --- interview_prep.md | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/interview_prep.md b/interview_prep.md index ba84d0c..c21497d 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -27,6 +27,28 @@ If you further increase the number of dice you roll, the edge cases become less ![](https://prwatech.in/blog/wp-content/uploads/2019/06/CetralLimitThm-1024x512.png) ### 4. What is the inter quartile range ? Why is it useful ? + +The interquartile range is a measure of where the “middle fifty” is in a data set. Where a range is a measure of where the beginning and end are in a set, an interquartile range is a measure of where the bulk of the values lie. That’s why it’s preferred over many other measures of spread when reporting things like school performance or SAT scores. + +The interquartile range formula is the first quartile subtracted from the third quartile: +IQR = Q3 – Q1. + +![](https://naysan.ca/wp-content/uploads/2020/06/box_plot_ref_needed.png) + +#### IQR as a test of normality in a distribution + +Use the interquartile range formula with the mean and standard deviation to test whether or not a population has a normal distribution. The formula to determine whether or not a population is normally distributed are: +Q1 – (σ z1) + X +Q3 – (σ z3) + X +Where Q1 is the first quartile, Q3 is the third quartile, σ is the standard deviation, z is the standard score (“z-score“) and X is the mean. In order to tell whether a population is normally distributed, solve both equations and then compare the results. If there is a significant difference between the results and the first or third quartiles, then the population is not normally distributed. + +#### IQR as an instrument to detect outliers and to determine the spread of data +The interquartile range and the quartile deviation refer to the same thing. They both mean the difference between the third quartile (Q3) and the first quartile (Q1). Both are also called midspread or middle fifty. + +Some of its applications include determining the spread of data. It is used in the construction of a box plot. It is a good indicator of spread because it is robust with breakpoint of 25%. A breakpoint percentage indicates the number of incorrect observations, before a parameter starts giving a wrong description of the data set. A 25% breakpoint is robust, as it needs a quarter of the data to be incorrect, before it reflects an incorrect spread. + +The IQR is also used to determine outliers to the data set. This is in conjuction with the box plot (or the box-and-whisker plot). Outliers are defined as values that are below Q1-1.5*IQR or above Q3+1.5*IQR. There are other methods that could be used to determine whether outliers can be eliminated from the data set. + ### 5. What is the difference between t-test and z-test ? Why is it useful ? ### 6. Why do we take n-1 when calculating sample variance? Why is it useful ? Read about Besel correction From 6d93a3350e3e0822a158e3de19243cb7266f9a60 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sun, 3 Jan 2021 13:57:01 +0530 Subject: [PATCH 10/49] Update interview_prep.md --- interview_prep.md | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/interview_prep.md b/interview_prep.md index c21497d..93dec6c 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -50,6 +50,18 @@ Some of its applications include determining the spread of data. It is used in t The IQR is also used to determine outliers to the data set. This is in conjuction with the box plot (or the box-and-whisker plot). Outliers are defined as values that are below Q1-1.5*IQR or above Q3+1.5*IQR. There are other methods that could be used to determine whether outliers can be eliminated from the data set. ### 5. What is the difference between t-test and z-test ? Why is it useful ? + +![](https://www.wallstreetmojo.com/wp-content/uploads/2019/01/Z-Test-vs-T-Test.png) + + +| Basis | Z Test | T-Test | +|-------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| +| Basic Definition | Z-test is a kind of hypothesis test which ascertains if the averages of the 2 datasets are different from each other when standard deviation or variance is given. | The t-test can be referred to as a kind of parametric test that is applied to an identity, how the averages of 2 sets of data differ from each other when the standard deviation or variance is not given. | +| Population Variance | The Population variance or standard deviation is known here. | The Population variance or standard deviation is unknown here. | +| Sample Size | The Sample size is large. | Here the Sample Size is small. | +| Key Assumptions | All data points are independent. Normal Distribution for Z, with an average zero and variance = 1. | All data points are not dependent. Sample values are to be recorded and taken accurately. | +| Based upon (a type of distribution) | Based on Normal distribution. | Based on Student-t distribution. | + ### 6. Why do we take n-1 when calculating sample variance? Why is it useful ? Read about Besel correction ### 7. What are the assumptions of the normal distribution ? Why is it useful ? From d1b0a91b415a2ca5cbdf5369d85be887f8c9cf13 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Mon, 4 Jan 2021 23:24:11 +0530 Subject: [PATCH 11/49] Create use_cases_insurnace.md --- use_cases_insurnace.md | 7 +++++++ 1 file changed, 7 insertions(+) create mode 100644 use_cases_insurnace.md diff --git a/use_cases_insurnace.md b/use_cases_insurnace.md new file mode 100644 index 0000000..8beb3e5 --- /dev/null +++ b/use_cases_insurnace.md @@ -0,0 +1,7 @@ +###Lapse management: Identifies policies that are likely to lapse, and how to approach the insured about maintaining the policy. +Recommendation engine: Given similar customers, discovers where individual insureds may have too much, or too little, insurance. Then, proactively help them get the right insurance for their current situation. +Assessor assistant: Once a car has been towed to a body shop, use computer vision to help the assessor identify issues which need to be fixed. This helps accuracy, speeds an assessment, and keeps the customer informed with any repairs. +Property analysis: Given images of a property, identifies structures on the property and any condition issues. Insurers can proactively help customers schedule repairs by identifying issues in their roofs, or suggest other coverage when new structures, like a swimming pool, are installed. +Fraud detection: Identifies claims which are potentially fraudulent. +Personalized offers: Improves the customer experience by offering relevant information about the coverage the insured may need based on life events, such as the birth of a child, purchase of a home or car. +Experience studies: Uses unsupervised machine learning to discover predictors in claims activity. This information can help set assumptions and feed into activities such as pricing models, risk analyses, and other actuarial analyses. From aeb0e2983e73dc02184bdcafbfbe34f5f69c5254 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Tue, 5 Jan 2021 00:17:57 +0530 Subject: [PATCH 12/49] Update interview_prep.md --- interview_prep.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/interview_prep.md b/interview_prep.md index 93dec6c..5c3437a 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -132,3 +132,13 @@ How to deal with them ? | Try getting additional features | Try getting more training examples | | | Try adding polynomial features | Try smaller set of features | | | Try to decrease the regularization parameter | Try to increase the regularization parameter | | + +### 28. What is right or left skewness ? +### 29. What is difference between bootstrapping and k-folds cross validation ? +overlapping of sample does not happen for k-folds cross validation +### 30. Which model is better: n_estimators=10 and n_estimators=30 ? +### 31. Why do we use activation functions in neural networks ? +### 32. What is the purpose of the optimizers ? +### 33. How does the stochastic gradient descent optimizer work ? + + From 1ee7330593356edb28b5a7adf9602376d97dbcdf Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Tue, 5 Jan 2021 09:39:20 +0530 Subject: [PATCH 13/49] Update use_cases_insurnace.md --- use_cases_insurnace.md | 54 ++++++++++++++++++++++++++++++++++++------ 1 file changed, 47 insertions(+), 7 deletions(-) diff --git a/use_cases_insurnace.md b/use_cases_insurnace.md index 8beb3e5..49c3e89 100644 --- a/use_cases_insurnace.md +++ b/use_cases_insurnace.md @@ -1,7 +1,47 @@ -###Lapse management: Identifies policies that are likely to lapse, and how to approach the insured about maintaining the policy. -Recommendation engine: Given similar customers, discovers where individual insureds may have too much, or too little, insurance. Then, proactively help them get the right insurance for their current situation. -Assessor assistant: Once a car has been towed to a body shop, use computer vision to help the assessor identify issues which need to be fixed. This helps accuracy, speeds an assessment, and keeps the customer informed with any repairs. -Property analysis: Given images of a property, identifies structures on the property and any condition issues. Insurers can proactively help customers schedule repairs by identifying issues in their roofs, or suggest other coverage when new structures, like a swimming pool, are installed. -Fraud detection: Identifies claims which are potentially fraudulent. -Personalized offers: Improves the customer experience by offering relevant information about the coverage the insured may need based on life events, such as the birth of a child, purchase of a home or car. -Experience studies: Uses unsupervised machine learning to discover predictors in claims activity. This information can help set assumptions and feed into activities such as pricing models, risk analyses, and other actuarial analyses. +#### Reference:- https://activewizards.com/blog/top-10-data-science-use-cases-in-insurance/ + +## Other use cases + +### Lapse management: +##### Identifies policies that are likely to lapse, and how to approach the insured about maintaining the policy. Calculate the probability to lapse + +### Recommendation engine: +##### Given similar customers, discovers where individual insureds may have too much, or too little, insurance. Then, proactively help them get the right insurance for their current situation. + +### Assessor assistant: +##### Once a car has been towed to a body shop, use computer vision to help the assessor identify issues which need to be fixed. This helps accuracy, speeds an assessment, and keeps the customer informed with any repairs. Car damage detection + +### Property analysis: +##### Given images of a property, identifies structures on the property and any condition issues. Insurers can proactively help customers schedule repairs by identifying issues in their roofs, or suggest other coverage when new structures, like a swimming pool, are installed. + +### Fraud detection: +##### Identifies claims which are potentially fraudulent. Rare events problem. Class imbalance is a huge challenge here + +### Personalized offers: +##### Improves the customer experience by offering relevant information about the coverage the insured may need based on life events, such as the birth of a child, purchase of a home or car. + +### Claims processing +##### Claims processing includes multiple tasks, including review, investigation, adjustment, remittance, or denial. While performing these tasks, numerous issues might occur: + +* Manual/inconsistent processing: Many claims processing tasks require human interaction that is prone to errors. +* Varying data formats: Customers send data in different formats to make claims. +* Changing regulation: Businesses need to accord in changing regulations promptly. Thus, constant staff training and process update are required for these companies. + +### Claims document processing +As customers make claims when they are in an uncomfortable position, customer experience and speed are critical in these processes. Thanks to document capture technologies, businesses can rapidly handle large volumes of documents required for claims processing tasks, detect fraudulent claims, and check if claims fit regulations. + +### Application processing +Application processing requires extracting information from a high volume of documents. While performing this task manually can take too long and prone to errors, document capture technologies enable insurance companies to automatically extract relevant data from application documents and accelerate insurance application processes with fewer errors and improved customer satisfaction. + +### Insurance pricing +AI can assess customers’ risk profiles based on lab testing, biometric data, claims data, patient-generated health data, and identify the optimal prices to quote with the right insurance plan. This would decrease the workflow in business operations and reduce costs while improving customer satisfaction. + +### Document creation +Insurance companies need to generate high volumes of documents, including specific information about the insurer. While creating these documents manually consume time and prone to errors, using AI and automation technologies can generate policy statements without mistakes. + +### Responding to customer queries +Conversational AI technologies can support insurance companies for faster replies to customer queries. For example, a South African insurance company, Hollard, has achieved 98% automation and reduced cost per transaction by 91%, according to its solution providers, LarcAI and UiPath. + + + + From 910faae3d4f5cb77601b355eb5a9fd039b2be1df Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Tue, 5 Jan 2021 10:10:33 +0530 Subject: [PATCH 14/49] Update interview_prep.md --- interview_prep.md | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/interview_prep.md b/interview_prep.md index 5c3437a..3f757d9 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -63,7 +63,29 @@ The IQR is also used to determine outliers to the data set. This is in conjuctio | Based upon (a type of distribution) | Based on Normal distribution. | Based on Student-t distribution. | ### 6. Why do we take n-1 when calculating sample variance? Why is it useful ? -Read about Besel correction +Read about Besel correction for more technical definition + +##### Intuitive explaination + +If you are giving the standard deviation of an entire population and not a sample you actually do divide by n. However, the denominator is not referencing the number of observations, it's actually referencing degrees of freedom, which is n-1. For you to understand degrees of freedom I would recommend this example using hats. + +Basically you divide by the number of things you need to 'know' before you can fill in the blanks yourself. If you are using an entire population, you need every single example as you can't just fill in the blanks. But if you have a sample, you can know all but the last one before you can fill in the blank. + +##### Example + +![](https://ae01.alicdn.com/kf/HTB1XFW0JXXXXXcKXFXXq6xXFXXX1/225440714/HTB1XFW0JXXXXXcKXFXXq6xXFXXX1.jpg) + +Imagine you have a huge bookshelf. You measure the total thickness of the first 6 books and it turns out to be 158mm. This means that the mean thickness of a book based on first 6 samples is 26.3mm. +Now you take out and measure the first book's thickness (one degree of freedom) and find that it is 22mm. This means that the remaining 5 books must have a total thickness of 136mm +Now you measure the second book (second degree of freedom) and find it to be 28mm. So you know that the remaining 4 books should have a total thickness of 108mm . +. +. +In this way, by the time you measure the thickness of the 5th book individually (5th degree of freedom) , you automatically know the thickness of the remaining 1 book. + +This means that you automatically know the thickness of 6th book even though you have measured only 5. Extrapolating this concept, In a sample of size n, you know the value of the n'th observation even though you have only taken (n-1) measurements. i.e, the opportunity to vary has been taken away for the n'th observation. + +This means that if you have measured (n-1) objects then the nth object has no freedom to vary. Therefore, degree of freedom is only (n-1) and not n. + ### 7. What are the assumptions of the normal distribution ? Why is it useful ? ### 8. What are the different approches to outlier detection ? How will you handle the outliers? Why is it useful ? ### 9. Where is RMSE a bad case ? How do we solve this ? From 6b2817883c4fa9bdefdf924e3d0b00668d2fde0f Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Wed, 6 Jan 2021 23:03:53 +0530 Subject: [PATCH 15/49] Update interview_prep.md --- interview_prep.md | 38 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 deletions(-) diff --git a/interview_prep.md b/interview_prep.md index 3f757d9..03bfd93 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -88,9 +88,43 @@ This means that if you have measured (n-1) objects then the nth object has no fr ### 7. What are the assumptions of the normal distribution ? Why is it useful ? ### 8. What are the different approches to outlier detection ? How will you handle the outliers? Why is it useful ? -### 9. Where is RMSE a bad case ? How do we solve this ? +### 9. How you assess OLS regression models ? +Three statistics are used in Ordinary Least Squares (OLS) regression to evaluate model fit: +* R-squared, +* the overall F-test, and +* the Root Mean Square Error (RMSE). + +All three are based on two sums of squares: Sum of Squares Total (SST) and Sum of Squares Error (SSE). SST measures how far the data are from the mean, and SSE measures how far the data are from the model’s predicted values. Different combinations of these two values provide different information about how the regression model compares to the mean model. + +##### R-squared and Adjusted R-squared + +The difference between SST and SSE is the improvement in prediction from the regression model, compared to the mean model. Dividing that difference by SST gives R-squared. It is the proportional improvement in prediction from the regression model, compared to the mean model. **It indicates the goodness of fit of the model.** + +R-squared has the useful property that its scale is intuitive: it ranges from zero to one, with zero indicating that the proposed model does not improve prediction over the mean model, and one indicating perfect prediction. Improvement in the regression model results in proportional increases in R-squared. + +One pitfall of R-squared is that it can only increase as predictors are added to the regression model. This increase is artificial when predictors are not actually improving the model’s fit. To remedy this, a related statistic, Adjusted R-squared, incorporates the model’s degrees of freedom. **Adjusted R-squared will decrease as predictors are added if the increase in model fit does not make up for the loss of degrees of freedom. Likewise, it will increase as predictors are added if the increase in model fit is worthwhile.** Adjusted R-squared should always be used with models with more than one predictor variable. It is interpreted as the proportion of total variance that is explained by the model. + +There are situations in which a high R-squared is not necessary or relevant. When the interest is in the relationship between variables, not in prediction, the R-square is less important. An example is a study on how religiosity affects health outcomes. A good result is a reliable relationship between religiosity and health. No one would expect that religion explains a high percentage of the variation in health, as health is affected by many other factors. Even if the model accounts for other variables known to affect health, such as income and age, an R-squared in the range of 0.10 to 0.15 is reasonable. + +![](https://miro.medium.com/max/1954/1*iFgJVgavYdENdtkssTS6pA.png) + +##### The F-test + +The F-test evaluates the null hypothesis that all regression coefficients are equal to zero versus the alternative that at least one is not. An equivalent null hypothesis is that R-squared equals zero. A significant F-test indicates that the observed R-squared is reliable and is not a spurious result of oddities in the data set. **Thus the F-test determines whether the proposed relationship between the response variable and the set of predictors is statistically reliable and can be useful when the research objective is either prediction or explanation.** + +##### RMSE + +The RMSE is the square root of the variance of the residuals. It indicates the absolute fit of the model to the data–how close the observed data points are to the model’s predicted values. **Whereas R-squared is a relative measure of fit, RMSE is an absolute measure of fit.** As the square root of a variance, RMSE can be interpreted as the standard deviation of the unexplained variance, and has the useful property of being in the same units as the response variable. **Lower values of RMSE indicate better fit. RMSE is a good measure of how accurately the model predicts the response, and it is the most important criterion for fit if the main purpose of the model is prediction.** + +##### NOTE: The best measure of model fit depends on the researcher’s objectives, and more than one are often useful. The statistics discussed above are applicable to regression models that use OLS estimation. Many types of regression models, however, such as mixed models, generalized linear models, and event history models, use maximum likelihood estimation. + ### 10. What are the loss functions used in logistic regression ? -log loss function + +![](https://miro.medium.com/max/548/1*rdBw0E-My8Gu3f_BOB6GMA.png) + +where y is the label (1 for event and 0 for non-event) and p(y) is the predicted probability of the event happening for all N observations. +Reading this formula, it tells you that, for each time the event occcurs (y=1), it adds log(p(y)) to the loss, that is, the log probability of event happening. Conversely, it adds log(1-p(y)), that is, the log probability of event not happening, for each non-event (y=0) + ### 11. Explain random forest in laymen terms ? ### 12. How does logisitc regression work in laymen terms ? ### 13. Why is logistic regression bad idea for multiclass classification ? From 31e26ea5cae7abcee59200086095fa242d9c398b Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Wed, 6 Jan 2021 23:22:55 +0530 Subject: [PATCH 16/49] Update interview_prep.md --- interview_prep.md | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/interview_prep.md b/interview_prep.md index 03bfd93..faa489c 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -126,6 +126,23 @@ where y is the label (1 for event and 0 for non-event) and p(y) is the predicted Reading this formula, it tells you that, for each time the event occcurs (y=1), it adds log(p(y)) to the loss, that is, the log probability of event happening. Conversely, it adds log(1-p(y)), that is, the log probability of event not happening, for each non-event (y=0) ### 11. Explain random forest in laymen terms ? + +Say you have three job offers and you wish to decide which is the best among them, you have the following criterion you use to shortlist a job offer like +* tools and technology +* company brand +* health insurance +* support for education +* compensation +* travel time +* joining bonus etc. + +You reach out to 10 of your connections on LinkedIn and ask them which is the best comapny to join based on 3 random criteria (for eg. c2, c3, c5) +You make different combinations of criteria while asking to different connections. At the end, you finally select company which is recommended the most from all the responses. + +##### This is how a random forest also works +![](https://miro.medium.com/max/690/0*Ry4NWdoTXjSjMfrE) + +you reach out to 50 of your different connections and ask them based on different param ### 12. How does logisitc regression work in laymen terms ? ### 13. Why is logistic regression bad idea for multiclass classification ? ### 14. How do you perform the train test split in a timeseries modelling ? From 3a0c8688208bda7dc864fbeeb2ded0fcdc74348c Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Wed, 6 Jan 2021 23:26:13 +0530 Subject: [PATCH 17/49] Update interview_prep.md --- interview_prep.md | 1 - 1 file changed, 1 deletion(-) diff --git a/interview_prep.md b/interview_prep.md index faa489c..990eb8f 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -142,7 +142,6 @@ You make different combinations of criteria while asking to different connection ##### This is how a random forest also works ![](https://miro.medium.com/max/690/0*Ry4NWdoTXjSjMfrE) -you reach out to 50 of your different connections and ask them based on different param ### 12. How does logisitc regression work in laymen terms ? ### 13. Why is logistic regression bad idea for multiclass classification ? ### 14. How do you perform the train test split in a timeseries modelling ? From baad68d2a531be6aecd75de5612bc15301cb2d2c Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Wed, 6 Jan 2021 23:28:28 +0530 Subject: [PATCH 18/49] Update interview_prep.md --- interview_prep.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/interview_prep.md b/interview_prep.md index 990eb8f..141d40a 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -140,7 +140,7 @@ You reach out to 10 of your connections on LinkedIn and ask them which is the be You make different combinations of criteria while asking to different connections. At the end, you finally select company which is recommended the most from all the responses. ##### This is how a random forest also works -![](https://miro.medium.com/max/690/0*Ry4NWdoTXjSjMfrE) +![](https://cdn.analyticsvidhya.com/wp-content/uploads/2020/02/rfc_vs_dt1.png) ### 12. How does logisitc regression work in laymen terms ? ### 13. Why is logistic regression bad idea for multiclass classification ? From 115f0a8f23b08686576705c85cdfd22ff8228aa4 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Wed, 10 Feb 2021 01:39:22 +0000 Subject: [PATCH 19/49] Bump cryptography from 3.2 to 3.3.2 Bumps [cryptography](https://github.com/pyca/cryptography) from 3.2 to 3.3.2. - [Release notes](https://github.com/pyca/cryptography/releases) - [Changelog](https://github.com/pyca/cryptography/blob/master/CHANGELOG.rst) - [Commits](https://github.com/pyca/cryptography/compare/3.2...3.3.2) Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index e26064b..c830d94 100644 --- a/requirements.txt +++ b/requirements.txt @@ -9,7 +9,7 @@ beautifulsoup4==4.6.3 certifi==2018.8.24 cffi==1.11.5 chardet==3.0.4 -cryptography==3.2 +cryptography==3.3.2 cycler==0.10.0 h5py==2.9.0 idna==2.7 From b1b208a79f75be8233261b88d10b33e7de57fbed Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 29 Mar 2021 18:43:38 +0000 Subject: [PATCH 20/49] Bump pygments from 2.3.1 to 2.7.4 Bumps [pygments](https://github.com/pygments/pygments) from 2.3.1 to 2.7.4. - [Release notes](https://github.com/pygments/pygments/releases) - [Changelog](https://github.com/pygments/pygments/blob/master/CHANGES) - [Commits](https://github.com/pygments/pygments/compare/2.3.1...2.7.4) Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index c830d94..8db7b8b 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,7 +1,7 @@ Keras==2.2.4 Keras-Preprocessing==1.0.5 PySocks==1.6.8 -Pygments==2.3.1 +Pygments==2.7.4 Quandl==3.4.5 asn1crypto==0.24.0 backcall==0.1.0 From 8dd8a1e3672c94e30687ab8bf1e5dc39dd57d176 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Wed, 9 Jun 2021 17:46:51 +0000 Subject: [PATCH 21/49] Bump pip from 10.0.1 to 19.2 Bumps [pip](https://github.com/pypa/pip) from 10.0.1 to 19.2. - [Release notes](https://github.com/pypa/pip/releases) - [Changelog](https://github.com/pypa/pip/blob/main/NEWS.rst) - [Commits](https://github.com/pypa/pip/compare/10.0.1...19.2) --- updated-dependencies: - dependency-name: pip dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 8db7b8b..b9324d9 100644 --- a/requirements.txt +++ b/requirements.txt @@ -24,7 +24,7 @@ pandas==0.23.4 patsy==0.5.0 pexpect==4.6.0 pickleshare==0.7.5 -pip==10.0.1 +pip==19.2 ptyprocess==0.6.0 pyOpenSSL==18.0.0 pycparser==2.19 From c3317dd57d96967a9934150f58039e02baa516df Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 15 Nov 2021 17:48:10 +0000 Subject: [PATCH 22/49] Bump pip from 19.2 to 21.1 Bumps [pip](https://github.com/pypa/pip) from 19.2 to 21.1. - [Release notes](https://github.com/pypa/pip/releases) - [Changelog](https://github.com/pypa/pip/blob/main/NEWS.rst) - [Commits](https://github.com/pypa/pip/compare/19.2...21.1) --- updated-dependencies: - dependency-name: pip dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index b9324d9..ed895c6 100644 --- a/requirements.txt +++ b/requirements.txt @@ -24,7 +24,7 @@ pandas==0.23.4 patsy==0.5.0 pexpect==4.6.0 pickleshare==0.7.5 -pip==19.2 +pip==21.1 ptyprocess==0.6.0 pyOpenSSL==18.0.0 pycparser==2.19 From 2664498ec023784f9ab5d5285fa3c41ad0f28f79 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Fri, 21 Jan 2022 19:40:42 +0000 Subject: [PATCH 23/49] Bump ipython from 7.2.0 to 7.16.3 Bumps [ipython](https://github.com/ipython/ipython) from 7.2.0 to 7.16.3. - [Release notes](https://github.com/ipython/ipython/releases) - [Commits](https://github.com/ipython/ipython/compare/7.2.0...7.16.3) --- updated-dependencies: - dependency-name: ipython dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index ed895c6..5a9cb4d 100644 --- a/requirements.txt +++ b/requirements.txt @@ -14,7 +14,7 @@ cycler==0.10.0 h5py==2.9.0 idna==2.7 inflection==0.3.1 -ipython==7.2.0 +ipython==7.16.3 jedi==0.13.2 kiwisolver==1.0.1 matplotlib==3.0.0 From d46d3a77b1aa7828433922328478ded0af4118bd Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Wed, 30 Mar 2022 04:29:43 +0000 Subject: [PATCH 24/49] Bump numpy from 1.15.2 to 1.21.0 Bumps [numpy](https://github.com/numpy/numpy) from 1.15.2 to 1.21.0. - [Release notes](https://github.com/numpy/numpy/releases) - [Changelog](https://github.com/numpy/numpy/blob/main/doc/HOWTO_RELEASE.rst.txt) - [Commits](https://github.com/numpy/numpy/compare/v1.15.2...v1.21.0) --- updated-dependencies: - dependency-name: numpy dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 5a9cb4d..e3781d9 100644 --- a/requirements.txt +++ b/requirements.txt @@ -19,7 +19,7 @@ jedi==0.13.2 kiwisolver==1.0.1 matplotlib==3.0.0 more-itertools==5.0.0 -numpy==1.15.2 +numpy==1.21.0 pandas==0.23.4 patsy==0.5.0 pexpect==4.6.0 From b3befe6daccae5289b23ce9b4dc700ad9c22437b Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Wed, 22 Jun 2022 05:13:07 +0000 Subject: [PATCH 25/49] Bump numpy from 1.21.0 to 1.22.0 Bumps [numpy](https://github.com/numpy/numpy) from 1.21.0 to 1.22.0. - [Release notes](https://github.com/numpy/numpy/releases) - [Changelog](https://github.com/numpy/numpy/blob/main/doc/HOWTO_RELEASE.rst) - [Commits](https://github.com/numpy/numpy/compare/v1.21.0...v1.22.0) --- updated-dependencies: - dependency-name: numpy dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index e3781d9..fb81870 100644 --- a/requirements.txt +++ b/requirements.txt @@ -19,7 +19,7 @@ jedi==0.13.2 kiwisolver==1.0.1 matplotlib==3.0.0 more-itertools==5.0.0 -numpy==1.21.0 +numpy==1.22.0 pandas==0.23.4 patsy==0.5.0 pexpect==4.6.0 From bc1edd25840b7a282de088d6e1c2b3d64f4ce64a Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Tue, 11 Oct 2022 18:51:29 +0530 Subject: [PATCH 26/49] Update interview_prep.md --- interview_prep.md | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/interview_prep.md b/interview_prep.md index 141d40a..b9f25af 100644 --- a/interview_prep.md +++ b/interview_prep.md @@ -86,7 +86,19 @@ This means that you automatically know the thickness of 6th book even though you This means that if you have measured (n-1) objects then the nth object has no freedom to vary. Therefore, degree of freedom is only (n-1) and not n. -### 7. What are the assumptions of the normal distribution ? Why is it useful ? +### 7. What are the assumptions of the linear regression model ? Why is it useful ? +We can divide the basic assumptions of linear regression into two categories based on whether the assumptions are about the explanatory variables (i.e. features) or the residuals. + +#### Assumptions about the explanatory variables (features): +* Linearity +* No multicollinearity + +#### Assumptions about the error terms (residuals): +* Gaussian distribution +* Homoskedasticity +* No autocorrelation +* Zero conditional mean + ### 8. What are the different approches to outlier detection ? How will you handle the outliers? Why is it useful ? ### 9. How you assess OLS regression models ? Three statistics are used in Ordinary Least Squares (OLS) regression to evaluate model fit: From c2e8b65528c68da00584a7d0f17138dbbebe5318 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Thu, 8 Dec 2022 03:00:44 +0000 Subject: [PATCH 27/49] Bump certifi from 2018.8.24 to 2022.12.7 Bumps [certifi](https://github.com/certifi/python-certifi) from 2018.8.24 to 2022.12.7. - [Release notes](https://github.com/certifi/python-certifi/releases) - [Commits](https://github.com/certifi/python-certifi/compare/2018.08.24...2022.12.07) --- updated-dependencies: - dependency-name: certifi dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index fb81870..358b9cf 100644 --- a/requirements.txt +++ b/requirements.txt @@ -6,7 +6,7 @@ Quandl==3.4.5 asn1crypto==0.24.0 backcall==0.1.0 beautifulsoup4==4.6.3 -certifi==2018.8.24 +certifi==2022.12.7 cffi==1.11.5 chardet==3.0.4 cryptography==3.3.2 From ac3a9d454e6b2f5337eb8b23d59d7ec1b675308b Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 26 Dec 2022 20:44:21 +0000 Subject: [PATCH 28/49] Bump wheel from 0.31.1 to 0.38.1 Bumps [wheel](https://github.com/pypa/wheel) from 0.31.1 to 0.38.1. - [Release notes](https://github.com/pypa/wheel/releases) - [Changelog](https://github.com/pypa/wheel/blob/main/docs/news.rst) - [Commits](https://github.com/pypa/wheel/compare/0.31.1...0.38.1) --- updated-dependencies: - dependency-name: wheel dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index fb81870..161cd8a 100644 --- a/requirements.txt +++ b/requirements.txt @@ -41,4 +41,4 @@ statsmodels==0.9.0 tornado==5.1.1 traitlets==4.3.2 wcwidth==0.1.7 -wheel==0.31.1 +wheel==0.38.1 From ff7d8668939a6c9f874bf97d3d5882a5cd4a5863 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 27 Dec 2022 15:34:35 +0000 Subject: [PATCH 29/49] Bump setuptools from 40.2.0 to 65.5.1 Bumps [setuptools](https://github.com/pypa/setuptools) from 40.2.0 to 65.5.1. - [Release notes](https://github.com/pypa/setuptools/releases) - [Changelog](https://github.com/pypa/setuptools/blob/main/CHANGES.rst) - [Commits](https://github.com/pypa/setuptools/compare/v40.2.0...v65.5.1) --- updated-dependencies: - dependency-name: setuptools dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index fb81870..1fd8a28 100644 --- a/requirements.txt +++ b/requirements.txt @@ -35,7 +35,7 @@ requests>=2.20.0 scikit-learn==0.20.0 scipy==1.1.0 seaborn==0.9.0 -setuptools==40.2.0 +setuptools==65.5.1 six==1.11.0 statsmodels==0.9.0 tornado==5.1.1 From 53bf9acbdaa1320bb4898b9b643e5057c2b382b5 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Fri, 10 Feb 2023 23:09:36 +0000 Subject: [PATCH 30/49] Bump ipython from 7.16.3 to 8.10.0 Bumps [ipython](https://github.com/ipython/ipython) from 7.16.3 to 8.10.0. - [Release notes](https://github.com/ipython/ipython/releases) - [Commits](https://github.com/ipython/ipython/compare/7.16.3...8.10.0) --- updated-dependencies: - dependency-name: ipython dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index fb81870..ce374c0 100644 --- a/requirements.txt +++ b/requirements.txt @@ -14,7 +14,7 @@ cycler==0.10.0 h5py==2.9.0 idna==2.7 inflection==0.3.1 -ipython==7.16.3 +ipython==8.10.0 jedi==0.13.2 kiwisolver==1.0.1 matplotlib==3.0.0 From d1b7d1f47a4a6267c3432b9fef42b64d674a0a68 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Sat, 25 Feb 2023 06:07:47 +0000 Subject: [PATCH 31/49] Bump cryptography from 3.3.2 to 39.0.1 Bumps [cryptography](https://github.com/pyca/cryptography) from 3.3.2 to 39.0.1. - [Release notes](https://github.com/pyca/cryptography/releases) - [Changelog](https://github.com/pyca/cryptography/blob/main/CHANGELOG.rst) - [Commits](https://github.com/pyca/cryptography/compare/3.3.2...39.0.1) --- updated-dependencies: - dependency-name: cryptography dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 358b9cf..cefb6fd 100644 --- a/requirements.txt +++ b/requirements.txt @@ -9,7 +9,7 @@ beautifulsoup4==4.6.3 certifi==2022.12.7 cffi==1.11.5 chardet==3.0.4 -cryptography==3.3.2 +cryptography==39.0.1 cycler==0.10.0 h5py==2.9.0 idna==2.7 From 25e8b590423b39402886a12dc0f573824a909ebe Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sat, 25 Feb 2023 11:42:33 +0530 Subject: [PATCH 32/49] Create dependabot.yml Adding new file --- .github/dependabot.yml | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 .github/dependabot.yml diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 0000000..a78b9c7 --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,11 @@ +# To get started with Dependabot version updates, you'll need to specify whic +# package ecosystems to update and where the package manifests are located. +# Please see the documentation for all configuration options: +# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates + +version: 2 +updates: + - package-ecosystem: "" # See documentation for possible values + directory: "/" # Location of package manifests + schedule: + interval: "weekly" From 4be2cd4109d65140f305fd5936fddf25a4526593 Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Sat, 25 Mar 2023 15:09:56 +0530 Subject: [PATCH 33/49] Add files via upload --- prec_rec_curve.py | 143 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 143 insertions(+) create mode 100644 prec_rec_curve.py diff --git a/prec_rec_curve.py b/prec_rec_curve.py new file mode 100644 index 0000000..7bde221 --- /dev/null +++ b/prec_rec_curve.py @@ -0,0 +1,143 @@ +import numpy as np +from sklearn.metrics import confusion_matrix, precision_score, recall_score +import matplotlib.pyplot as plt +import matplotlib.patches as ptch + +# Appendix A - working with single threshold +pred_scores = [0.7, 0.3, 0.5, 0.6, 0.55, 0.9, 0.4, 0.2, 0.4, 0.3] +y_true = ["positive", "negative", "negative", "positive", "positive", "positive", "negative", "positive", "negative", "positive"] + +# To convert the scores into a class label, a threshold is used. +# When the score is equal to or above the threshold, the sample is classified as one class. +# Otherwise, it is classified as the other class. +# Suppose a sample is Positive if its score is above or equal to the threshold. Otherwise, it is Negative. +# The next block of code converts the scores into class labels with a threshold of 0.5. + +threshold = 0.5 + +y_pred = ["positive" if score >= threshold else "negative" for score in pred_scores] +print(y_pred) + +r = np.flip(confusion_matrix(y_true, y_pred)) +print("\n# Confusion Matrix (From Left to Right & Top to Bottom: \nTrue Positive, False Negative, \nFalse Positive, True Negative)") +print(r) + +# Remember that the higher the precision, the more confident the model is when it classifies a sample as Positive. +# Higher the recall, the more positive samples the model correctly classified as Positive. + +precision = precision_score(y_true=y_true, y_pred=y_pred, pos_label="positive") +print("\n# Precision = 4/(4+1)") +print(precision) + +recall = recall_score(y_true=y_true, y_pred=y_pred, pos_label="positive") +print("\n# Recall = 4/(4+2)") +print(recall) + +# Appendix B - working with multiple thresholds +y_true = ["positive", "negative", "negative", "positive", "positive", "positive", "negative", "positive", "negative", "positive", "positive", "positive", "positive", "negative", "negative", "negative"] + +pred_scores = [0.7, 0.3, 0.5, 0.6, 0.55, 0.9, 0.4, 0.2, 0.4, 0.3, 0.7, 0.5, 0.8, 0.2, 0.3, 0.35] + +thresholds = np.arange(start=0.2, stop=0.7, step=0.05) + +# Due to the importance of both precision and recall, there is a precision-recall curve that shows +# the tradeoff between the precision and recall values for different thresholds. +# This curve helps to select the best threshold to maximize both metrics + +def precision_recall_curve(y_true, pred_scores, thresholds): + precisions = [] + recalls = [] + f1_scores = [] + + for threshold in thresholds: + y_pred = ["positive" if score >= threshold else "negative" for score in pred_scores] + + precision = precision_score(y_true=y_true, y_pred=y_pred, pos_label="positive") + recall = recall_score(y_true=y_true, y_pred=y_pred, pos_label="positive") + f1_score = (2 * precision * recall) / (precision + recall) + + precisions.append(precision) + recalls.append(recall) + f1_scores.append(f1_score) + + return precisions, recalls, f1_scores + +precisions, recalls, f1_scores = precision_recall_curve(y_true=y_true, + pred_scores=pred_scores, + thresholds=thresholds) + +print("\nRecall:: Precision :: F1-Score",) +for p, r, f in zip(precisions, recalls, f1_scores): + print(round(r,4),"\t::\t",round(p,4),"\t::\t",round(f,4)) + +# np.max() returns the max. value in the array +# np.argmax() will return the index of the value found by np.max() + +print('Best F1-Score: ', np.max(f1_scores)) +idx_best_f1 = np.argmax(f1_scores) +print('\nBest threshold: ', thresholds[idx_best_f1]) +print('Index of threshold: ', idx_best_f1) + +# Can disable comment to display the plot + +# plt.plot(recalls, precisions, linewidth=4, color="red") +# plt.scatter(recalls[idx_best_f1], precisions[idx_best_f1], zorder=1, linewidth=6) +# plt.xlabel("Recall", fontsize=12, fontweight='bold') +# plt.ylabel("Precision", fontsize=12, fontweight='bold') +# plt.title("Precision-Recall Curve", fontsize=15, fontweight="bold") +# plt.show() + +# Appendix C - average precision (AP) +precisions, recalls, f1_scores = precision_recall_curve(y_true=y_true, + pred_scores=pred_scores, + thresholds=thresholds) + +precisions.append(1) +recalls.append(0) + +precisions = np.array(precisions) +recalls = np.array(recalls) + +print('\nRecall ::',recalls) +print('Precision ::',precisions) + +AP = np.sum((recalls[:-1] - recalls[1:]) * precisions[:-1]) +print("\nAP --", AP) + +# Appendix D - Intersection over Union + +# gt_box -- ground-truth bounding box +# pred_box -- prediction bounding box +def intersection_over_union(gt_box, pred_box): + + inter_box_top_left = [max(gt_box[0], pred_box[0]), max(gt_box[1], pred_box[1])] + + print("\ninter_box_top_left:", inter_box_top_left) + print("gt_box:", gt_box) + print("pred_box:", pred_box) + inter_box_bottom_right = [min(gt_box[0]+gt_box[2], pred_box[0]+pred_box[2]), min(gt_box[1]+gt_box[3], pred_box[1]+pred_box[3])] + print("inter_box_bottom_right:", inter_box_bottom_right) + + inter_box_w = inter_box_bottom_right[0] - inter_box_top_left[0] + print("inter_box_w:", inter_box_w) + inter_box_h = inter_box_bottom_right[1] - inter_box_top_left[1] + print("inter_box_h:", inter_box_h) + + intersection = inter_box_w * inter_box_h + union = gt_box[2] * gt_box[3] + pred_box[2] * pred_box[3] - intersection + + iou = intersection / union + + return iou, intersection, union + +gt_box1 = [320, 220, 680, 900] +pred_box1 = [500, 320, 550, 700] + +gt_box2 = [645, 130, 310, 320] +pred_box2 = [500, 60, 310, 320] + +iou1 = intersection_over_union(gt_box1, pred_box1) +print("\nIOU1 ::", iou1) + +iou2 = intersection_over_union(gt_box2, pred_box2) +print("\nIOU2 ::", iou2) \ No newline at end of file From bb15cdf6389dff507763a5ac78e523d528b1e98f Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Tue, 4 Apr 2023 15:25:21 +0530 Subject: [PATCH 34/49] Create SECURITY.md --- SECURITY.md | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 SECURITY.md diff --git a/SECURITY.md b/SECURITY.md new file mode 100644 index 0000000..034e848 --- /dev/null +++ b/SECURITY.md @@ -0,0 +1,21 @@ +# Security Policy + +## Supported Versions + +Use this section to tell people about which versions of your project are +currently being supported with security updates. + +| Version | Supported | +| ------- | ------------------ | +| 5.1.x | :white_check_mark: | +| 5.0.x | :x: | +| 4.0.x | :white_check_mark: | +| < 4.0 | :x: | + +## Reporting a Vulnerability + +Use this section to tell people how to report a vulnerability. + +Tell them where to go, how often they can expect to get an update on a +reported vulnerability, what to expect if the vulnerability is accepted or +declined, etc. From a6fbb3db2be99581bcddd29c0d95c162e121807b Mon Sep 17 00:00:00 2001 From: Amogh Singhal Date: Mon, 12 Jun 2023 12:07:25 +0530 Subject: [PATCH 35/49] Update README.md --- README.md | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/README.md b/README.md index 4da9732..9e3482e 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,10 @@ # Machine-Learning-with-Python ![GitHub stars](https://img.shields.io/github/stars/devAmoghS/Machine-Learning-with-Python?style=for-the-badge) ![GitHub forks](https://img.shields.io/github/forks/devAmoghS/Machine-Learning-with-Python?label=Forks&style=for-the-badge) + +## Star History + +[![Star History Chart](https://api.star-history.com/svg?repos=devAmoghS/Machine-Learning-with-Python&type=Date)](https://star-history.com/#devAmoghS/Machine-Learning-with-Python&Date) + + ![alt text](https://media.istockphoto.com/vectors/machine-learning-3-step-infographic-artificial-intelligence-machine-vector-id962219860?k=6&m=962219860&s=612x612&w=0&h=yricYyUqZbILMHp3IvtenS3xbRDhu1w1u5kk2az5tbo=) ## Small scale machine learning projects to understand the core concepts (order: oldest to newest) From 17e89d10c1a055cf7533657f7a7e7100c6755841 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Thu, 6 Jul 2023 21:25:48 +0000 Subject: [PATCH 36/49] Bump scipy from 1.1.0 to 1.10.0 Bumps [scipy](https://github.com/scipy/scipy) from 1.1.0 to 1.10.0. - [Release notes](https://github.com/scipy/scipy/releases) - [Commits](https://github.com/scipy/scipy/compare/v1.1.0...v1.10.0) --- updated-dependencies: - dependency-name: scipy dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index a6641fd..8d6a647 100644 --- a/requirements.txt +++ b/requirements.txt @@ -33,7 +33,7 @@ python-dateutil==2.7.3 pytz==2018.5 requests>=2.20.0 scikit-learn==0.20.0 -scipy==1.1.0 +scipy==1.10.0 seaborn==0.9.0 setuptools==65.5.1 six==1.11.0 From f93afe24b8b72b23c6f67919002436f2e43f62ad Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Thu, 20 Jul 2023 13:10:54 +0000 Subject: [PATCH 37/49] Bump pygments from 2.7.4 to 2.15.0 Bumps [pygments](https://github.com/pygments/pygments) from 2.7.4 to 2.15.0. - [Release notes](https://github.com/pygments/pygments/releases) - [Changelog](https://github.com/pygments/pygments/blob/master/CHANGES) - [Commits](https://github.com/pygments/pygments/compare/2.7.4...2.15.0) --- updated-dependencies: - dependency-name: pygments dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index a6641fd..c002b50 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,7 +1,7 @@ Keras==2.2.4 Keras-Preprocessing==1.0.5 PySocks==1.6.8 -Pygments==2.7.4 +Pygments==2.15.0 Quandl==3.4.5 asn1crypto==0.24.0 backcall==0.1.0 From ffaf0c4d0aafa65483982137aef0a67adc394562 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Wed, 2 Aug 2023 01:32:45 +0000 Subject: [PATCH 38/49] Bump cryptography from 39.0.1 to 41.0.3 Bumps [cryptography](https://github.com/pyca/cryptography) from 39.0.1 to 41.0.3. - [Changelog](https://github.com/pyca/cryptography/blob/main/CHANGELOG.rst) - [Commits](https://github.com/pyca/cryptography/compare/39.0.1...41.0.3) --- updated-dependencies: - dependency-name: cryptography dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index a6641fd..a152178 100644 --- a/requirements.txt +++ b/requirements.txt @@ -9,7 +9,7 @@ beautifulsoup4==4.6.3 certifi==2022.12.7 cffi==1.11.5 chardet==3.0.4 -cryptography==39.0.1 +cryptography==41.0.3 cycler==0.10.0 h5py==2.9.0 idna==2.7 From 2e13fda52748ca4dec2c36d016082368e2db3a97 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 14 Aug 2023 22:03:29 +0000 Subject: [PATCH 39/49] Bump tornado from 5.1.1 to 6.3.3 Bumps [tornado](https://github.com/tornadoweb/tornado) from 5.1.1 to 6.3.3. - [Changelog](https://github.com/tornadoweb/tornado/blob/master/docs/releases.rst) - [Commits](https://github.com/tornadoweb/tornado/compare/v5.1.1...v6.3.3) --- updated-dependencies: - dependency-name: tornado dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index a6641fd..df8dfee 100644 --- a/requirements.txt +++ b/requirements.txt @@ -38,7 +38,7 @@ seaborn==0.9.0 setuptools==65.5.1 six==1.11.0 statsmodels==0.9.0 -tornado==5.1.1 +tornado==6.3.3 traitlets==4.3.2 wcwidth==0.1.7 wheel==0.38.1 From e8dbf024ed64e1ee240244246700a8a821b74235 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Thu, 17 Aug 2023 01:39:09 +0000 Subject: [PATCH 40/49] Bump certifi from 2022.12.7 to 2023.7.22 Bumps [certifi](https://github.com/certifi/python-certifi) from 2022.12.7 to 2023.7.22. - [Commits](https://github.com/certifi/python-certifi/compare/2022.12.07...2023.07.22) --- updated-dependencies: - dependency-name: certifi dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index a6641fd..8f71574 100644 --- a/requirements.txt +++ b/requirements.txt @@ -6,7 +6,7 @@ Quandl==3.4.5 asn1crypto==0.24.0 backcall==0.1.0 beautifulsoup4==4.6.3 -certifi==2022.12.7 +certifi==2023.7.22 cffi==1.11.5 chardet==3.0.4 cryptography==39.0.1 From 1a671db581c679d179ef3585c6a725feacc12805 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 25 Jun 2024 11:35:42 +0000 Subject: [PATCH 41/49] Bump pip from 21.1 to 23.3 Bumps [pip](https://github.com/pypa/pip) from 21.1 to 23.3. - [Changelog](https://github.com/pypa/pip/blob/main/NEWS.rst) - [Commits](https://github.com/pypa/pip/compare/21.1...23.3) --- updated-dependencies: - dependency-name: pip dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 6622752..25351e5 100644 --- a/requirements.txt +++ b/requirements.txt @@ -24,7 +24,7 @@ pandas==0.23.4 patsy==0.5.0 pexpect==4.6.0 pickleshare==0.7.5 -pip==21.1 +pip==23.3 ptyprocess==0.6.0 pyOpenSSL==18.0.0 pycparser==2.19 From ece2528697d6b28dee7718e4a127206c274a83b0 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 25 Jun 2024 11:36:28 +0000 Subject: [PATCH 42/49] Bump cryptography from 39.0.1 to 42.0.4 Bumps [cryptography](https://github.com/pyca/cryptography) from 39.0.1 to 42.0.4. - [Changelog](https://github.com/pyca/cryptography/blob/main/CHANGELOG.rst) - [Commits](https://github.com/pyca/cryptography/compare/39.0.1...42.0.4) --- updated-dependencies: - dependency-name: cryptography dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index fc5d79d..441b518 100644 --- a/requirements.txt +++ b/requirements.txt @@ -9,7 +9,7 @@ beautifulsoup4==4.6.3 certifi==2023.7.22 cffi==1.11.5 chardet==3.0.4 -cryptography==41.0.3 +cryptography==42.0.4 cycler==0.10.0 h5py==2.9.0 idna==2.7 From 75c3a6eb23031e62731551690b2326d73ab40b0e Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 25 Jun 2024 11:36:37 +0000 Subject: [PATCH 43/49] Bump tornado from 5.1.1 to 6.4.1 Bumps [tornado](https://github.com/tornadoweb/tornado) from 5.1.1 to 6.4.1. - [Changelog](https://github.com/tornadoweb/tornado/blob/master/docs/releases.rst) - [Commits](https://github.com/tornadoweb/tornado/compare/v5.1.1...v6.4.1) --- updated-dependencies: - dependency-name: tornado dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index fc5d79d..a2f9cf2 100644 --- a/requirements.txt +++ b/requirements.txt @@ -38,7 +38,7 @@ seaborn==0.9.0 setuptools==65.5.1 six==1.11.0 statsmodels==0.9.0 -tornado==6.3.3 +tornado==6.4.1 traitlets==4.3.2 wcwidth==0.1.7 wheel==0.38.1 From 0ee256998f26d57e216edbbcb58516f301703fb1 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 25 Jun 2024 11:36:54 +0000 Subject: [PATCH 44/49] Bump scikit-learn from 0.20.0 to 1.5.0 Bumps [scikit-learn](https://github.com/scikit-learn/scikit-learn) from 0.20.0 to 1.5.0. - [Release notes](https://github.com/scikit-learn/scikit-learn/releases) - [Commits](https://github.com/scikit-learn/scikit-learn/compare/0.20.0...1.5.0) --- updated-dependencies: - dependency-name: scikit-learn dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index fc5d79d..fc2d7ab 100644 --- a/requirements.txt +++ b/requirements.txt @@ -32,7 +32,7 @@ pyparsing==2.2.1 python-dateutil==2.7.3 pytz==2018.5 requests>=2.20.0 -scikit-learn==0.20.0 +scikit-learn==1.5.0 scipy==1.10.0 seaborn==0.9.0 setuptools==65.5.1 From d3f3928dcb80cb9db05e0699f5b0527bf607614a Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 25 Jun 2024 11:40:17 +0000 Subject: [PATCH 45/49] Bump idna from 2.7 to 3.7 Bumps [idna](https://github.com/kjd/idna) from 2.7 to 3.7. - [Release notes](https://github.com/kjd/idna/releases) - [Changelog](https://github.com/kjd/idna/blob/master/HISTORY.rst) - [Commits](https://github.com/kjd/idna/compare/v2.7...v3.7) --- updated-dependencies: - dependency-name: idna dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index ee8d009..c83a46d 100644 --- a/requirements.txt +++ b/requirements.txt @@ -12,7 +12,7 @@ chardet==3.0.4 cryptography==42.0.4 cycler==0.10.0 h5py==2.9.0 -idna==2.7 +idna==3.7 inflection==0.3.1 ipython==8.10.0 jedi==0.13.2 From e9a498caf9fbdf485242e58c5378096a256e594f Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Mon, 15 Jul 2024 17:29:35 +0000 Subject: [PATCH 46/49] Bump setuptools from 65.5.1 to 70.0.0 Bumps [setuptools](https://github.com/pypa/setuptools) from 65.5.1 to 70.0.0. - [Release notes](https://github.com/pypa/setuptools/releases) - [Changelog](https://github.com/pypa/setuptools/blob/main/NEWS.rst) - [Commits](https://github.com/pypa/setuptools/compare/v65.5.1...v70.0.0) --- updated-dependencies: - dependency-name: setuptools dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index c83a46d..caf00e7 100644 --- a/requirements.txt +++ b/requirements.txt @@ -35,7 +35,7 @@ requests>=2.20.0 scikit-learn==1.5.0 scipy==1.10.0 seaborn==0.9.0 -setuptools==65.5.1 +setuptools==70.0.0 six==1.11.0 statsmodels==0.9.0 tornado==6.4.1 From 8ea82d59a2fa94fab100469c37cebab57b1ff259 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Fri, 2 Aug 2024 16:20:13 +0000 Subject: [PATCH 47/49] Bump keras from 2.2.4 to 2.13.1 Bumps [keras](https://github.com/keras-team/keras) from 2.2.4 to 2.13.1. - [Release notes](https://github.com/keras-team/keras/releases) - [Commits](https://github.com/keras-team/keras/compare/2.2.4...v2.13.1) --- updated-dependencies: - dependency-name: keras dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index c83a46d..21914c8 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,4 +1,4 @@ -Keras==2.2.4 +Keras==2.13.1 Keras-Preprocessing==1.0.5 PySocks==1.6.8 Pygments==2.15.0 From 406a19afb38c4338fc9fb9ff73baf8354146c6c7 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 1 Apr 2025 02:26:44 +0000 Subject: [PATCH 48/49] Bump tornado from 6.4.1 to 6.4.2 Bumps [tornado](https://github.com/tornadoweb/tornado) from 6.4.1 to 6.4.2. - [Changelog](https://github.com/tornadoweb/tornado/blob/v6.4.2/docs/releases.rst) - [Commits](https://github.com/tornadoweb/tornado/compare/v6.4.1...v6.4.2) --- updated-dependencies: - dependency-name: tornado dependency-version: 6.4.2 dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 126de70..16ba325 100644 --- a/requirements.txt +++ b/requirements.txt @@ -38,7 +38,7 @@ seaborn==0.9.0 setuptools==70.0.0 six==1.11.0 statsmodels==0.9.0 -tornado==6.4.1 +tornado==6.4.2 traitlets==4.3.2 wcwidth==0.1.7 wheel==0.38.1 From 15d9c864a779fe43de90d2bd2424e6597bbfdd07 Mon Sep 17 00:00:00 2001 From: "dependabot[bot]" <49699333+dependabot[bot]@users.noreply.github.com> Date: Tue, 1 Apr 2025 02:26:46 +0000 Subject: [PATCH 49/49] Bump cryptography from 42.0.4 to 44.0.1 Bumps [cryptography](https://github.com/pyca/cryptography) from 42.0.4 to 44.0.1. - [Changelog](https://github.com/pyca/cryptography/blob/main/CHANGELOG.rst) - [Commits](https://github.com/pyca/cryptography/compare/42.0.4...44.0.1) --- updated-dependencies: - dependency-name: cryptography dependency-version: 44.0.1 dependency-type: direct:production ... Signed-off-by: dependabot[bot] --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 126de70..61ddb84 100644 --- a/requirements.txt +++ b/requirements.txt @@ -9,7 +9,7 @@ beautifulsoup4==4.6.3 certifi==2023.7.22 cffi==1.11.5 chardet==3.0.4 -cryptography==42.0.4 +cryptography==44.0.1 cycler==0.10.0 h5py==2.9.0 idna==3.7